diff --git a/bib/bibliography.bib b/bib/bibliography.bib
index 7430b35a7647c06fd73ff04143a45f944869e8b3..81d85a36cfff8bc4876854996e8f5a33577bdb6b 100644
--- a/bib/bibliography.bib
+++ b/bib/bibliography.bib
@@ -49,6 +49,43 @@
file = {/Users/wasmer/Nextcloud/Zotero/Alberi et al_2018_The 2019 materials by design roadmap.pdf}
}
+@article{allenMachineLearningMaterial2022,
+ title = {Machine Learning of Material Properties: {{Predictive}} and Interpretable Multilinear Models},
+ shorttitle = {Machine Learning of Material Properties},
+ author = {Allen, Alice E. A. and Tkatchenko, Alexandre},
+ date = {2022-05-06},
+ journaltitle = {Science Advances},
+ volume = {8},
+ number = {18},
+ pages = {eabm7185},
+ publisher = {{American Association for the Advancement of Science}},
+ doi = {10.1126/sciadv.abm7185},
+ url = {https://www.science.org/doi/full/10.1126/sciadv.abm7185},
+ urldate = {2023-03-19},
+ abstract = {Machine learning models can provide fast and accurate predictions of material properties but often lack transparency. Interpretability techniques can be used with black box solutions, or alternatively, models can be created that are directly interpretable. We revisit material datasets used in several works and demonstrate that simple linear combinations of nonlinear basis functions can be created, which have comparable accuracy to the kernel and neural network approaches originally used. Linear solutions can accurately predict the bandgap and formation energy of transparent conducting oxides, the spin states for transition metal complexes, and the formation energy for elpasolite structures. We demonstrate how linear solutions can provide interpretable predictive models and highlight the new insights that can be found when a model can be directly understood from its coefficients and functional form. Furthermore, we discuss how to recognize when intrinsically interpretable solutions may be the best route to interpretability.},
+ keywords = {/unread,AML,kernel methods,linear regression,ML,model comparison,NN,spin-dependent,TODO,transition metals,XAI},
+ file = {/Users/wasmer/Nextcloud/Zotero/Allen_Tkatchenko_2022_Machine learning of material properties.pdf}
+}
+
+@article{alredMachineLearningElectron2018,
+ title = {Machine Learning Electron Density in Sulfur Crosslinked Carbon Nanotubes},
+ author = {Alred, John M. and Bets, Ksenia V. and Xie, Yu and Yakobson, Boris I.},
+ date = {2018-09-29},
+ journaltitle = {Composites Science and Technology},
+ shortjournal = {Composites Science and Technology},
+ series = {Carbon Nanotube Composites for Structural Applications},
+ volume = {166},
+ pages = {3--9},
+ issn = {0266-3538},
+ doi = {10.1016/j.compscitech.2018.03.035},
+ url = {https://www.sciencedirect.com/science/article/pii/S0266353817330300},
+ urldate = {2023-03-23},
+ abstract = {Mechanical strengthening of composite materials that include carbon nanotubes (CNT) requires strong inter-bonding to achieve significant CNT-CNT or CNT-matrix load transfer. The same principle is applicable to the improvement of CNT bundles and calls for covalent crosslinks between individual tubes. In this work, sulfur crosslinks are studied using a combination of density functional theory (DFT) and classical molecular dynamics (MD). Atomic chains of at least two sulfur atoms or more are shown to be stable between both zigzag and armchair CNTs. All types of crosslinked CNTs exhibit significantly improved load transfer. Moreover, sulfur crosslinks show evidence of a cooperative self-healing mechanism allowing for links to rebond once broken leading to sustained load transfer under shear loading. Additionally, a general approach for utilizing machine learning for assessing the ground state electron density is developed and applied to these sulfur crosslinked CNTs.},
+ langid = {english},
+ keywords = {AML,carbon,CNT,CP2K,grid-based descriptors,ML,ML-DFT,ML-ESM,NN,PBE,prediction of electron density,random forest,TensorFlow},
+ file = {/Users/wasmer/Nextcloud/Zotero/Alred et al_2018_Machine learning electron density in sulfur crosslinked carbon nanotubes.pdf;/Users/wasmer/Zotero/storage/879XU9RI/S0266353817330300.html}
+}
+
@article{amorosoInterplaySingleIonTwoIon2021,
title = {Interplay between {{Single-Ion}} and {{Two-Ion Anisotropies}} in {{Frustrated 2D Semiconductors}} and {{Tuning}} of {{Magnetic Structures Topology}}},
author = {Amoroso, Danila and Barone, Paolo and Picozzi, Silvia},
@@ -93,9 +130,9 @@
shorttitle = {Cormorant},
author = {Anderson, Brandon and Hy, Truong-Son and Kondor, Risi},
date = {2019-11-25},
- number = {arXiv:1906.04015},
- eprint = {arXiv:1906.04015},
+ eprint = {1906.04015},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.1906.04015},
url = {http://arxiv.org/abs/1906.04015},
urldate = {2022-10-04},
@@ -109,9 +146,9 @@
title = {Prediction-{{Powered Inference}}},
author = {Angelopoulos, Anastasios N. and Bates, Stephen and Fannjiang, Clara and Jordan, Michael I. and Zrnic, Tijana},
date = {2023-02-16},
- number = {arXiv:2301.09633},
- eprint = {arXiv:2301.09633},
+ eprint = {2301.09633},
eprinttype = {arxiv},
+ eprintclass = {cs, q-bio, stat},
doi = {10.48550/arXiv.2301.09633},
url = {http://arxiv.org/abs/2301.09633},
urldate = {2023-03-01},
@@ -121,6 +158,27 @@
file = {/Users/wasmer/Nextcloud/Zotero/Angelopoulos et al_2023_Prediction-Powered Inference.pdf;/Users/wasmer/Zotero/storage/VUQUZZ32/2301.html}
}
+@article{artrithBestPracticesMachine2021,
+ title = {Best Practices in Machine Learning for Chemistry},
+ author = {Artrith, Nongnuch and Butler, Keith T. and Coudert, François-Xavier and Han, Seungwu and Isayev, Olexandr and Jain, Anubhav and Walsh, Aron},
+ date = {2021-06},
+ journaltitle = {Nature Chemistry},
+ shortjournal = {Nat. Chem.},
+ volume = {13},
+ number = {6},
+ pages = {505--508},
+ publisher = {{Nature Publishing Group}},
+ issn = {1755-4349},
+ doi = {10.1038/s41557-021-00716-z},
+ url = {https://www.nature.com/articles/s41557-021-00716-z},
+ urldate = {2023-03-20},
+ abstract = {Statistical tools based on machine learning are becoming integrated into chemistry research workflows. We discuss the elements necessary to train reliable, repeatable and reproducible models, and recommend a set of guidelines for machine learning reports.},
+ issue = {6},
+ langid = {english},
+ keywords = {active learning,AML,benchmarking,best practices,checklist,chemistry,guidelines,HDNNP,iterative learning scheme,ML,ML-ESM,MLP,publishing,review},
+ file = {/Users/wasmer/Zotero/storage/EMW6UVAA/Artrith et al. - 2021 - Best practices in machine learning for chemistry.pdf}
+}
+
@article{artrithEfficientAccurateMachinelearning2017,
title = {Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species},
author = {Artrith, Nongnuch and Urban, Alexander and Ceder, Gerbrand},
@@ -138,6 +196,14 @@
file = {/Users/wasmer/Nextcloud/Zotero/Artrith et al_2017_Efficient and accurate machine-learning interpolation of atomic energies in.pdf;/Users/wasmer/Zotero/storage/77VRNTN7/Artrith et al. - 2017 - Efficient and accurate machine-learning interpolat.pdf;/Users/wasmer/Zotero/storage/RL7TSVEA/PhysRevB.96.html}
}
+@online{AssessingDataScience,
+ title = {Assessing Data Science Research via Data Science Maturity Levels: {{Patterns}}},
+ url = {https://www.cell.com/patterns/dsml},
+ urldate = {2023-04-13},
+ keywords = {/unread},
+ file = {/Users/wasmer/Zotero/storage/EMN72WHE/dsml.html}
+}
+
@article{atzGeometricDeepLearning2021,
title = {Geometric Deep Learning on Molecular Representations},
author = {Atz, Kenneth and Grisoni, Francesca and Schneider, Gisbert},
@@ -344,7 +410,6 @@
title = {The {{Design Space}} of {{E}}(3)-{{Equivariant Atom-Centered Interatomic Potentials}}},
author = {Batatia, Ilyes and Batzner, Simon and Kovács, Dávid Péter and Musaelian, Albert and Simm, Gregor N. C. and Drautz, Ralf and Ortner, Christoph and Kozinsky, Boris and Csányi, Gábor},
date = {2022-05-13},
- number = {arXiv:2205.06643},
eprint = {2205.06643},
eprinttype = {arxiv},
eprintclass = {cond-mat, physics:physics, stat},
@@ -362,9 +427,9 @@
shorttitle = {{{MACE}}},
author = {Batatia, Ilyes and Kovács, Dávid Péter and Simm, Gregor N. C. and Ortner, Christoph and Csányi, Gábor},
date = {2022-06-15},
- number = {arXiv:2206.07697},
- eprint = {arXiv:2206.07697},
+ eprint = {2206.07697},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics, stat},
doi = {10.48550/arXiv.2206.07697},
url = {http://arxiv.org/abs/2206.07697},
urldate = {2022-09-25},
@@ -391,6 +456,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Batra et al_2020_Emerging materials intelligence ecosystems propelled by machine learning.pdf;/Users/wasmer/Zotero/storage/A3A6TGKC/s41578-020-00255-y.html}
}
+@article{batraGeneralAtomicNeighborhood2019,
+ title = {General {{Atomic Neighborhood Fingerprint}} for {{Machine Learning-Based Methods}}},
+ author = {Batra, Rohit and Tran, Huan Doan and Kim, Chiho and Chapman, James and Chen, Lihua and Chandrasekaran, Anand and Ramprasad, Rampi},
+ date = {2019-06-27},
+ journaltitle = {The Journal of Physical Chemistry C},
+ shortjournal = {J. Phys. Chem. C},
+ volume = {123},
+ number = {25},
+ pages = {15859--15866},
+ publisher = {{American Chemical Society}},
+ issn = {1932-7447},
+ doi = {10.1021/acs.jpcc.9b03925},
+ url = {https://doi.org/10.1021/acs.jpcc.9b03925},
+ urldate = {2023-04-13},
+ abstract = {To facilitate chemical space exploration for material screening or to accelerate computationally expensive first-principles simulations, inexpensive surrogate models that capture electronic, atomistic, or macroscopic materials properties have become an increasingly popular tool over the last decade. The most fundamental quantity common across all such machine learning (ML)-based methods is the fingerprint used to numerically represent a material or its structure. To increase the learning capability of the ML methods, the common practice is to construct fingerprints that satisfy the same symmetry relations as displayed by the target material property of interest (for which the ML model is being developed). Thus, in this work, we present a general, simple, and elegant fingerprint that can be used to learn different electronic/atomistic/structural properties, irrespective of their scalar, vector, or tensorial nature. This fingerprint is based on the concept of multipole terms and can be systematically increased in sophistication to achieve a desired level of accuracy. Using the examples of Al, C, and hafnia (HfO2), we demonstrate the applicability of this fingerprint to easily classify different atomistic environments, such as phases, surfaces, point defects, and so forth. Furthermore, we demonstrate the generality and effectiveness of this fingerprint by building an accurate, yet inexpensive, ML-based potential energy model for the case of Al using a reference data set that is obtained from density functional theory computations. Finally, we note that the fingerprint definition presented here has applications in fields beyond materials informatics, such as structure prediction, identification of defects, and detection of new crystal phases.},
+ keywords = {AML,descriptors,invariance,MD,ML,MLP,with-data},
+ file = {/Users/wasmer/Nextcloud/Zotero/Batra et al_2019_General Atomic Neighborhood Fingerprint for Machine Learning-Based Methods.pdf;/Users/wasmer/Zotero/storage/4XDSVIN6/acs.jpcc.html}
+}
+
@unpublished{batznerEquivariantGraphNeural2021,
title = {E(3)-{{Equivariant Graph Neural Networks}} for {{Data-Efficient}} and {{Accurate Interatomic Potentials}}},
author = {Batzner, Simon and Musaelian, Albert and Sun, Lixin and Geiger, Mario and Mailoa, Jonathan P. and Kornbluth, Mordechai and Molinari, Nicola and Smidt, Tess E. and Kozinsky, Boris},
@@ -528,6 +612,27 @@
file = {/Users/wasmer/Nextcloud/Zotero/Behler_2016_Perspective.pdf}
}
+@article{benderEvaluationGuidelinesMachine2022,
+ title = {Evaluation Guidelines for Machine Learning Tools in the Chemical Sciences},
+ author = {Bender, Andreas and Schneider, Nadine and Segler, Marwin and Patrick Walters, W. and Engkvist, Ola and Rodrigues, Tiago},
+ date = {2022-06},
+ journaltitle = {Nature Reviews Chemistry},
+ shortjournal = {Nat Rev Chem},
+ volume = {6},
+ number = {6},
+ pages = {428--442},
+ publisher = {{Nature Publishing Group}},
+ issn = {2397-3358},
+ doi = {10.1038/s41570-022-00391-9},
+ url = {https://www.nature.com/articles/s41570-022-00391-9},
+ urldate = {2023-04-10},
+ abstract = {Machine learning (ML) promises to tackle the grand challenges in chemistry and speed up the generation, improvement and/or ordering of research hypotheses. Despite the overarching applicability of ML workflows, one usually finds diverse evaluation study designs. The current heterogeneity in evaluation techniques and metrics leads to difficulty in (or the impossibility of) comparing and assessing the relevance of new algorithms. Ultimately, this may delay the digitalization of chemistry at scale and confuse method developers, experimentalists, reviewers and journal editors. In this Perspective, we critically discuss a set of method development and evaluation guidelines for different types of ML-based publications, emphasizing supervised learning. We provide a diverse collection of examples from various authors and disciplines in chemistry. While taking into account varying accessibility across research groups, our recommendations focus on reporting completeness and standardizing comparisons between tools. We aim to further contribute to improved ML transparency and credibility by suggesting a checklist of retro-/prospective tests and dissecting their importance. We envisage that the wide adoption and continuous update of best practices will encourage an informed use of ML on real-world problems related to the chemical sciences.},
+ issue = {6},
+ langid = {english},
+ keywords = {AML,benchmarking,best practices,chemistry,classification,evaluation metrics,guidelines,MAE,ML,model evaluation,MSE,R2,regression,regression metrics,reproducibility,SHAP,Supervised learning,unsupervised learning,XAI},
+ file = {/Users/wasmer/Nextcloud/Zotero/Bender et al_2022_Evaluation guidelines for machine learning tools in the chemical sciences.pdf}
+}
+
@article{bengioRepresentationLearningReview2013,
title = {Representation {{Learning}}: {{A Review}} and {{New Perspectives}}},
shorttitle = {Representation {{Learning}}},
@@ -614,6 +719,23 @@
file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Bigi et al_2022_A smooth basis for atomistic machine learning.pdf}
}
+@online{bigiWignerKernelsBodyordered2023,
+ title = {Wigner Kernels: Body-Ordered Equivariant Machine Learning without a Basis},
+ shorttitle = {Wigner Kernels},
+ author = {Bigi, Filippo and Pozdnyakov, Sergey N. and Ceriotti, Michele},
+ date = {2023-03-07},
+ eprint = {2303.04124},
+ eprinttype = {arxiv},
+ eprintclass = {physics, stat},
+ doi = {10.48550/arXiv.2303.04124},
+ url = {http://arxiv.org/abs/2303.04124},
+ urldate = {2023-04-13},
+ abstract = {Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that have been pursued, the description of local atomic environments in terms of their neighbor densities has been used widely and very succesfully. We propose a novel density-based method which involves computing ``Wigner kernels''. These are fully equivariant and body-ordered kernels that can be computed iteratively with a cost that is independent of the radial-chemical basis and grows only linearly with the maximum body-order considered. This is in marked contrast to feature-space models, which comprise an exponentially-growing number of terms with increasing order of correlations. We present several examples of the accuracy of models based on Wigner kernels in chemical applications, for both scalar and tensorial targets, reaching state-of-the-art accuracy on the popular QM9 benchmark dataset, and we discuss the broader relevance of these ideas to equivariant geometric machine-learning.},
+ pubstate = {preprint},
+ keywords = {ACE,Allegro,AML,benchmarking,body-order,descriptor comparison,descriptors,DimeNet++,equivariant,GPR,KRR,lambda-SOAP,ML,MLP,model comparison,molecules,MPNN,NICE,PAiNN,QM9,representation learning,SA-GPR,SOAP,SphereNet,tensorial target,Wigner kernel},
+ file = {/Users/wasmer/Nextcloud/Zotero/Bigi et al_2023_Wigner kernels.pdf;/Users/wasmer/Zotero/storage/LERSCPN4/2303.html}
+}
+
@online{bishopPlenaryFifthParadigm2022,
type = {Video},
title = {Plenary: {{The}} Fifth Paradigm of Scientific Discovery},
@@ -734,7 +856,6 @@
title = {Multilayer Atomic Cluster Expansion for Semi-Local Interactions},
author = {Bochkarev, Anton and Lysogorskiy, Yury and Ortner, Christoph and Csányi, Gábor and Drautz, Ralf},
date = {2022-05-17},
- number = {arXiv:2205.08177},
eprint = {2205.08177},
eprinttype = {arxiv},
eprintclass = {cond-mat},
@@ -751,9 +872,9 @@
title = {Multilayer Atomic Cluster Expansion for Semi-Local Interactions},
author = {Bochkarev, Anton and Lysogorskiy, Yury and Ortner, Christoph and Csányi, Gábor and Drautz, Ralf},
date = {2022-05-17},
- number = {arXiv:2205.08177},
- eprint = {arXiv:2205.08177},
+ eprint = {2205.08177},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2205.08177},
url = {http://arxiv.org/abs/2205.08177},
urldate = {2022-09-29},
@@ -787,9 +908,9 @@
title = {Efficient Prediction of {{3D}} Electron Densities Using Machine Learning},
author = {Bogojeski, Mihail and Brockherde, Felix and Vogt-Maranto, Leslie and Li, Li and Tuckerman, Mark E. and Burke, Kieron and Müller, Klaus-Robert},
date = {2018-11-15},
- number = {arXiv:1811.06255},
- eprint = {arXiv:1811.06255},
+ eprint = {1811.06255},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.1811.06255},
url = {http://arxiv.org/abs/1811.06255},
urldate = {2022-07-08},
@@ -816,11 +937,27 @@
abstract = {Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal~⋅~mol−1 with presently-available functionals. Ab initio methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. In this paper, we leverage machine learning to calculate coupled-cluster energies from DFT densities, reaching quantum chemical accuracy (errors below 1 kcal~⋅~mol−1) on test data. Moreover, density-based Δ-learning (learning only the correction to a standard DFT calculation, termed Δ-DFT~) significantly reduces the amount of training data required, particularly when molecular symmetries are included. The robustness of Δ-DFT~ is highlighted by correcting “on the fly†DFT-based molecular dynamics (MD) simulations of resorcinol (C6H4(OH)2) to obtain MD trajectories with coupled-cluster accuracy. We conclude, therefore, that Δ-DFT~ facilitates running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT fails.},
issue = {1},
langid = {english},
- keywords = {_tablet,2-step model,CCSD(T),coupled cluster,Delta,delta learning,DFT,HK map,KKR,ML,ML-DFA,ML-DFT,ML-ESM,ML-HK map,molecules,prediction of electron density,with-code,Δ-machine learning},
+ keywords = {_tablet,2-step model,AML,CC,CCSD(T),coupled cluster,Delta,delta learning,DFT,HK map,KKR,ML,ML-DFA,ML-DFT,ML-ESM,ML-HK map,molecules,multi-step model,prediction of electron density,with-code,Δ-machine learning},
annotation = {Bandiera\_abtest: a Cc\_license\_type: cc\_by Cg\_type: Nature Research Journals Primary\_atype: Research Subject\_term: Computational chemistry;Computational science Subject\_term\_id: computational-chemistry;computational-science},
file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Bogojeski et al_2020_Quantum chemical accuracy from density functional approximations via machine.pdf}
}
+@online{bommasaniOpportunitiesRisksFoundation2022,
+ title = {On the {{Opportunities}} and {{Risks}} of {{Foundation Models}}},
+ author = {Bommasani, Rishi and Hudson, Drew A. and Adeli, Ehsan and Altman, Russ and Arora, Simran and family=Arx, given=Sydney, prefix=von, useprefix=true and Bernstein, Michael S. and Bohg, Jeannette and Bosselut, Antoine and Brunskill, Emma and Brynjolfsson, Erik and Buch, Shyamal and Card, Dallas and Castellon, Rodrigo and Chatterji, Niladri and Chen, Annie and Creel, Kathleen and Davis, Jared Quincy and Demszky, Dora and Donahue, Chris and Doumbouya, Moussa and Durmus, Esin and Ermon, Stefano and Etchemendy, John and Ethayarajh, Kawin and Fei-Fei, Li and Finn, Chelsea and Gale, Trevor and Gillespie, Lauren and Goel, Karan and Goodman, Noah and Grossman, Shelby and Guha, Neel and Hashimoto, Tatsunori and Henderson, Peter and Hewitt, John and Ho, Daniel E. and Hong, Jenny and Hsu, Kyle and Huang, Jing and Icard, Thomas and Jain, Saahil and Jurafsky, Dan and Kalluri, Pratyusha and Karamcheti, Siddharth and Keeling, Geoff and Khani, Fereshte and Khattab, Omar and Koh, Pang Wei and Krass, Mark and Krishna, Ranjay and Kuditipudi, Rohith and Kumar, Ananya and Ladhak, Faisal and Lee, Mina and Lee, Tony and Leskovec, Jure and Levent, Isabelle and Li, Xiang Lisa and Li, Xuechen and Ma, Tengyu and Malik, Ali and Manning, Christopher D. and Mirchandani, Suvir and Mitchell, Eric and Munyikwa, Zanele and Nair, Suraj and Narayan, Avanika and Narayanan, Deepak and Newman, Ben and Nie, Allen and Niebles, Juan Carlos and Nilforoshan, Hamed and Nyarko, Julian and Ogut, Giray and Orr, Laurel and Papadimitriou, Isabel and Park, Joon Sung and Piech, Chris and Portelance, Eva and Potts, Christopher and Raghunathan, Aditi and Reich, Rob and Ren, Hongyu and Rong, Frieda and Roohani, Yusuf and Ruiz, Camilo and Ryan, Jack and Ré, Christopher and Sadigh, Dorsa and Sagawa, Shiori and Santhanam, Keshav and Shih, Andy and Srinivasan, Krishnan and Tamkin, Alex and Taori, Rohan and Thomas, Armin W. and Tramèr, Florian and Wang, Rose E. and Wang, William and Wu, Bohan and Wu, Jiajun and Wu, Yuhuai and Xie, Sang Michael and Yasunaga, Michihiro and You, Jiaxuan and Zaharia, Matei and Zhang, Michael and Zhang, Tianyi and Zhang, Xikun and Zhang, Yuhui and Zheng, Lucia and Zhou, Kaitlyn and Liang, Percy},
+ date = {2022-07-12},
+ eprint = {2108.07258},
+ eprinttype = {arxiv},
+ eprintclass = {cs},
+ doi = {10.48550/arXiv.2108.07258},
+ url = {http://arxiv.org/abs/2108.07258},
+ urldate = {2023-04-14},
+ abstract = {AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.},
+ pubstate = {preprint},
+ keywords = {/unread,few-shot learning,foundation models,General ML,ML,transfer learning,transformer,zero-shot learning},
+ file = {/Users/wasmer/Nextcloud/Zotero/Bommasani et al_2022_On the Opportunities and Risks of Foundation Models.pdf;/Users/wasmer/Zotero/storage/72DPHWW4/2108.html}
+}
+
@article{borchaniSurveyMultioutputRegression2015,
title = {A Survey on Multi-Output Regression},
author = {Borchani, Hanen and Varando, Gherardo and Bielza, Concha and Larrañaga, Pedro},
@@ -907,7 +1044,6 @@
title = {Lie {{Point Symmetry Data Augmentation}} for {{Neural PDE Solvers}}},
author = {Brandstetter, Johannes and Welling, Max and Worrall, Daniel E.},
date = {2022-05-29},
- number = {arXiv:2202.07643},
eprint = {2202.07643},
eprinttype = {arxiv},
eprintclass = {cs},
@@ -1033,9 +1169,9 @@
shorttitle = {Lies {{My Teacher Told Me About Density Functional Theory}}},
author = {Burke, Kieron and Kozlowski, John},
date = {2021-10-18},
- number = {arXiv:2108.11534},
- eprint = {arXiv:2108.11534},
+ eprint = {2108.11534},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2108.11534},
url = {http://arxiv.org/abs/2108.11534},
urldate = {2022-07-10},
@@ -1065,6 +1201,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Bystrom_Kozinsky_2022_CIDER.pdf}
}
+@online{bystromNonlocalMachineLearnedExchange2023,
+ title = {Nonlocal {{Machine-Learned Exchange Functional}} for {{Molecules}} and {{Solids}}},
+ author = {Bystrom, Kyle and Kozinsky, Boris},
+ date = {2023-03-01},
+ eprint = {2303.00682},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.2303.00682},
+ url = {http://arxiv.org/abs/2303.00682},
+ urldate = {2023-03-20},
+ abstract = {The design of better exchange-correlation (XC) functionals for Density Functional Theory (DFT) is a central challenge of modern electronic structure theory. However, current developments are limited by the mathematical form of the functional, with efficient semi-local functionals being inaccurate for many technologically important systems and the more accurate hybrid functionals being too expensive for large solid-state systems due to the use of the exact exchange operator. In this work, we use physics-informed machine learning to design an exchange functional that is both orbital-dependent and nonlocal, but which can be evaluated at roughly the cost of semi-local functionals and is significantly faster than hybrid DFT in plane-wave codes. By training functionals with several different feature sets, we elucidate the roles of orbital-dependent and nonlocal features in learning the exchange energy and determine that both types of features provide vital and independently important information to the model. Having trained our new exchange functional with an expressive, nonlocal feature set, we substitute it into existing hybrid functionals to achieve hybrid-DFT accuracy on thermochemical benchmark sets and improve the accuracy of band gap predictions over semi-local DFT. To demonstrate the scalability of our approach as well as the practical benefits of improved band gap prediction, we compute charged defect transition levels in silicon using large supercells. Due to its transferability and computational efficiency for both molecular and extended systems, our model overcomes the cost-accuracy trade-off between semi-local and hybrid DFT, and our general approach provides a feasible path toward a universal exchange-correlation functional with post-hybrid DFT accuracy and semi-local DFT cost.},
+ pubstate = {preprint},
+ keywords = {all-electron,AML,CIDER,DFT,ML,ML-DFA,ML-ESM,PAW,plane-wave,prediction of Exc},
+ file = {/Users/wasmer/Zotero/storage/FUN9D5UI/Bystrom and Kozinsky - 2023 - Nonlocal Machine-Learned Exchange Functional for M.pdf;/Users/wasmer/Zotero/storage/9YGJRHDG/2303.html}
+}
+
@article{calderonAFLOWStandardHighthroughput2015,
title = {The {{AFLOW}} Standard for High-Throughput Materials Science Calculations},
author = {Calderon, Camilo E. and Plata, Jose J. and Toher, Cormac and Oses, Corey and Levy, Ohad and Fornari, Marco and Natan, Amir and Mehl, Michael J. and Hart, Gus and Buongiorno Nardelli, Marco and Curtarolo, Stefano},
@@ -1318,9 +1470,9 @@
title = {A Data-Driven Interpretation of the Stability of Molecular Crystals},
author = {Cersonsky, Rose K. and Pakhnova, Maria and Engel, Edgar A. and Ceriotti, Michele},
date = {2022-12-22},
- number = {arXiv:2209.10709},
- eprint = {arXiv:2209.10709},
+ eprint = {2209.10709},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics, stat},
doi = {10.48550/arXiv.2209.10709},
url = {http://arxiv.org/abs/2209.10709},
urldate = {2023-01-23},
@@ -1369,7 +1521,7 @@
langid = {english},
keywords = {_tablet,custom structural descriptors,descriptors,DFT,FCNN,grid-based descriptors,LDOS,ML,ML-DFT,ML-ESM,models,NN,prediction from structure,prediction of electron density,prediction of LDOS,RNN},
annotation = {Bandiera\_abtest: a Cc\_license\_type: cc\_by Cg\_type: Nature Research Journals Primary\_atype: Research Subject\_term: Computational methods;Electronic structure;Theory and computation Subject\_term\_id: computational-methods;electronic-structure;theory-and-computation},
- file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Chandrasekaran et al_2019_Solving the electronic structure problem with machine learning.pdf;/Users/wasmer/Zotero/storage/TL92B668/s41524-019-0162-7.html}
+ file = {/Users/wasmer/Nextcloud/Zotero/Chandrasekaran et al_2019_Solving the electronic structure problem with machine learning.pdf;/Users/wasmer/Nextcloud/Zotero/Chandrasekaran et al_2019_Solving the electronic structure problem with machine learning2.pdf;/Users/wasmer/Zotero/storage/TL92B668/s41524-019-0162-7.html}
}
@article{changExperimentalObservationQuantum2013,
@@ -1421,6 +1573,21 @@
file = {/Users/wasmer/Nextcloud/Zotero/Chen et al_2019_Graph Networks as a Universal Machine Learning Framework for Molecules and.pdf}
}
+@online{chenPhysicsInspiredMachineLearning2023,
+ title = {Physics-{{Inspired Machine Learning}} of {{Localized Intensive Properties}}},
+ author = {Chen, Ke and Kunkel, Christian and Cheng, Bingqing and Reuter, Karsten and Margraf, Johannes T.},
+ date = {2023-02-21},
+ eprinttype = {ChemRxiv},
+ doi = {10.26434/chemrxiv-2023-h9qdj},
+ url = {https://chemrxiv.org/engage/chemrxiv/article-details/63f330899da0bc6b333d2812},
+ urldate = {2023-03-20},
+ abstract = {Machine learning (ML) has been widely applied to chemical property prediction, most prominently for the energies and forces in molecules and materials. The strong interest in predicting energies in particular has led to a local energy-based paradigm for modern atomistic ML models, which ensures size-extensivity and a linear scaling of computational cost with system size. However, many electronic properties (such as excitation energies or ionization energies) do not necessarily scale linearly with system size and may even be spatially localized. Using size-extensive models in these cases can lead to large errors. In this work, we explore different strategies for learning intensive and localized properties, using HOMO energies in organic molecules as a representative test case. In particular, we analyze the pooling functions that atomistic neural networks use to predict molecular properties, and suggest an orbital weighted average (OWA) approach that enables the accurate prediction of orbital energies and locations.},
+ langid = {english},
+ pubstate = {preprint},
+ keywords = {AML,HOMO,intensive properties,localized electronic structure,ML,model comparison,MPNN,pooling,prediction of intensive properties,prediction of orbital energies,SchNet,SchNetPack,SOAP},
+ file = {/Users/wasmer/Zotero/storage/HAJCMMQ8/Chen et al. - 2023 - Physics-Inspired Machine Learning of Localized Int.pdf}
+}
+
@unpublished{chenUniversalGraphDeep2022,
title = {A {{Universal Graph Deep Learning Interatomic Potential}} for the {{Periodic Table}}},
author = {Chen, Chi and Ong, Shyue Ping},
@@ -1541,6 +1708,23 @@
file = {/Users/wasmer/Nextcloud/Zotero/Cobelli et al_2022_Inversion of the chemical environment representations.pdf;/Users/wasmer/Zotero/storage/A6MH6ZIG/2201.html}
}
+@article{cohenInsightsCurrentLimitations2008,
+ title = {Insights into {{Current Limitations}} of {{Density Functional Theory}}},
+ author = {Cohen, Aron J. and Mori-Sánchez, Paula and Yang, Weitao},
+ date = {2008-08-08},
+ journaltitle = {Science},
+ volume = {321},
+ number = {5890},
+ pages = {792--794},
+ publisher = {{American Association for the Advancement of Science}},
+ doi = {10.1126/science.1158722},
+ url = {https://www.science.org/doi/10.1126/science.1158722},
+ urldate = {2023-04-11},
+ abstract = {Density functional theory of electronic structure is widely and successfully applied in simulations throughout engineering and sciences. However, for many predicted properties, there are spectacular failures that can be traced to the delocalization error and static correlation error of commonly used approximations. These errors can be characterized and understood through the perspective of fractional charges and fractional spins introduced recently. Reducing these errors will open new frontiers for applications of density functional theory.},
+ keywords = {/unread,DFA,DFT,fractional charges,fractional spin,limits of DFT,physics,self-interaction},
+ file = {/Users/wasmer/Nextcloud/Zotero/Cohen et al_2008_Insights into Current Limitations of Density Functional Theory.pdf}
+}
+
@article{collinsHumanGenomeProject2003,
title = {The {{Human Genome Project}}: {{Lessons}} from {{Large-Scale Biology}}},
shorttitle = {The {{Human Genome Project}}},
@@ -1614,6 +1798,39 @@
file = {/Users/wasmer/Zotero/storage/5MTYTHXV/S0927025612000687.html}
}
+@online{damewoodRepresentationsMaterialsMachine2023,
+ title = {Representations of {{Materials}} for {{Machine Learning}}},
+ author = {Damewood, James and Karaguesian, Jessica and Lunger, Jaclyn R. and Tan, Aik Rui and Xie, Mingrou and Peng, Jiayu and Gómez-Bombarelli, Rafael},
+ date = {2023-01-20},
+ eprint = {2301.08813},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2301.08813},
+ url = {http://arxiv.org/abs/2301.08813},
+ urldate = {2023-03-19},
+ abstract = {High-throughput data generation methods and machine learning (ML) algorithms have given rise to a new era of computational materials science by learning relationships among composition, structure, and properties and by exploiting such relations for design. However, to build these connections, materials data must be translated into a numerical form, called a representation, that can be processed by a machine learning model. Datasets in materials science vary in format (ranging from images to spectra), size, and fidelity. Predictive models vary in scope and property of interests. Here, we review context-dependent strategies for constructing representations that enable the use of materials as inputs or outputs of machine learning models. Furthermore, we discuss how modern ML techniques can learn representations from data and transfer chemical and physical information between tasks. Finally, we outline high-impact questions that have not been fully resolved and thus, require further investigation.},
+ pubstate = {preprint},
+ keywords = {/unread,AML,defects,descriptors,disordered,materials,ML,review,review-of-descriptors,TODO},
+ file = {/Users/wasmer/Nextcloud/Zotero/Damewood et al_2023_Representations of Materials for Machine Learning.pdf;/Users/wasmer/Zotero/storage/7JZ95596/2301.html}
+}
+
+@online{dankaModALModularActive2018,
+ title = {{{modAL}}: {{A}} Modular Active Learning Framework for {{Python}}},
+ shorttitle = {{{modAL}}},
+ author = {Danka, Tivadar and Horvath, Peter},
+ date = {2018-12-12},
+ eprint = {1805.00979},
+ eprinttype = {arxiv},
+ eprintclass = {cs, stat},
+ doi = {10.48550/arXiv.1805.00979},
+ url = {http://arxiv.org/abs/1805.00979},
+ urldate = {2023-04-10},
+ abstract = {modAL is a modular active learning framework for Python, aimed to make active learning research and practice simpler. Its distinguishing features are (i) clear and modular object oriented design (ii) full compatibility with scikit-learn models and workflows. These features make fast prototyping and easy extensibility possible, aiding the development of real-life active learning pipelines and novel algorithms as well. modAL is fully open source, hosted on GitHub at https://github.com/cosmic-cortex/modAL. To assure code quality, extensive unit tests are provided and continuous integration is applied. In addition, a detailed documentation with several tutorials are also available for ease of use. The framework is available in PyPI and distributed under the MIT license.},
+ pubstate = {preprint},
+ keywords = {active learning,General ML,library,Python},
+ file = {/Users/wasmer/Nextcloud/Zotero/Danka_Horvath_2018_modAL.pdf;/Users/wasmer/Zotero/storage/BRMUZWH3/1805.html}
+}
+
@unpublished{darbyCompressingLocalAtomic2021,
title = {Compressing Local Atomic Neighbourhood Descriptors},
author = {Darby, James P. and Kermode, James R. and Csányi, Gábor},
@@ -1653,9 +1870,9 @@
title = {Tensor-Reduced Atomic Density Representations},
author = {Darby, James P. and Kovács, Dávid P. and Batatia, Ilyes and Caro, Miguel A. and Hart, Gus L. W. and Ortner, Christoph and Csányi, Gábor},
date = {2022-10-01},
- number = {arXiv:2210.01705},
- eprint = {arXiv:2210.01705},
+ eprint = {2210.01705},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2210.01705},
url = {http://arxiv.org/abs/2210.01705},
urldate = {2022-10-05},
@@ -1746,6 +1963,26 @@
file = {/Users/wasmer/Nextcloud/Zotero/Degrave et al_2022_Magnetic control of tokamak plasmas through deep reinforcement learning.pdf;/Users/wasmer/Zotero/storage/U6PRS6KM/s41586-021-04301-9.html}
}
+@article{delrioEfficientDeepLearning2020,
+ title = {An {{Efficient Deep Learning Scheme To Predict}} the {{Electronic Structure}} of {{Materials}} and {{Molecules}}: {{The Example}} of {{Graphene-Derived Allotropes}}},
+ shorttitle = {An {{Efficient Deep Learning Scheme To Predict}} the {{Electronic Structure}} of {{Materials}} and {{Molecules}}},
+ author = {family=Rio, given=Beatriz G., prefix=del, useprefix=true and Kuenneth, Christopher and Tran, Huan Doan and Ramprasad, Rampi},
+ date = {2020-11-12},
+ journaltitle = {The Journal of Physical Chemistry A},
+ shortjournal = {J. Phys. Chem. A},
+ volume = {124},
+ number = {45},
+ pages = {9496--9502},
+ publisher = {{American Chemical Society}},
+ issn = {1089-5639},
+ doi = {10.1021/acs.jpca.0c07458},
+ url = {https://doi.org/10.1021/acs.jpca.0c07458},
+ urldate = {2023-04-13},
+ abstract = {Computations based on density functional theory (DFT) are transforming various aspects of materials research and discovery. However, the effort required to solve the central equation of DFT, namely the Kohn–Sham equation, which remains a major obstacle for studying large systems with hundreds of atoms in a practical amount of time with routine computational resources. Here, we propose a deep learning architecture that systematically learns the input–output behavior of the Kohn–Sham equation and predicts the electronic density of states, a primary output of DFT calculations, with unprecedented speed and chemical accuracy. The algorithm also adapts and progressively improves in predictive power and versatility as it is exposed to new diverse atomic configurations. We demonstrate this capability for a diverse set of carbon allotropes spanning a large configurational and phase space. The electronic density of states, along with the electronic charge density, may be used downstream to predict a variety of materials properties, bypassing the Kohn–Sham equation, leading to an ultrafast and high-fidelity DFT emulator.},
+ keywords = {AML,carbon,defects,disordered,grid-based descriptors,materials,ML,ML-DFT,ML-ESM,NN,prediction of DOS,prediction of electron density,vacancies,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/del Rio et al_2020_An Efficient Deep Learning Scheme To Predict the Electronic Structure of.pdf;/Users/wasmer/Zotero/storage/46EGTQLS/acs.jpca.html}
+}
+
@article{dengImageNetLargescaleHierarchical2009,
title = {{{ImageNet}}: {{A}} Large-Scale Hierarchical Image Database},
shorttitle = {{{ImageNet}}},
@@ -1961,9 +2198,9 @@
title = {The {{Jacobi-Legendre}} Potential},
author = {Domina, Michelangelo and Patil, Urvesh and Cobelli, Matteo and Sanvito, Stefano},
date = {2022-08-22},
- number = {arXiv:2208.10292},
- eprint = {arXiv:2208.10292},
+ eprint = {2208.10292},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2208.10292},
url = {http://arxiv.org/abs/2208.10292},
urldate = {2022-09-05},
@@ -2011,9 +2248,9 @@
title = {A {{Machine-Learning Surrogate Model}} for Ab Initio {{Electronic Correlations}} at {{Extreme Conditions}}},
author = {Dornheim, Tobias and Moldabekov, Zhandos and Cangi, Attila},
date = {2021-04-07},
- number = {arXiv:2104.02941},
- eprint = {arXiv:2104.02941},
+ eprint = {2104.02941},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2104.02941},
url = {http://arxiv.org/abs/2104.02941},
urldate = {2023-02-15},
@@ -2147,9 +2384,9 @@
title = {Atomic Cluster Expansion and Wave Function Representations},
author = {Drautz, Ralf and Ortner, Christoph},
date = {2022-06-22},
- number = {arXiv:2206.11375},
- eprint = {arXiv:2206.11375},
+ eprint = {2206.11375},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2206.11375},
url = {http://arxiv.org/abs/2206.11375},
urldate = {2022-06-28},
@@ -2198,7 +2435,7 @@
shorttitle = {The {{NOMAD}} Laboratory},
author = {Draxl, Claudia and Scheffler, Matthias},
date = {2019-05},
- shortjournal = {J. Phys. Mater.},
+ journaltitle = {J. Phys. Mater.},
volume = {2},
number = {3},
pages = {036001},
@@ -2287,7 +2524,6 @@
title = {Low {{Dimensional Invariant Embeddings}} for {{Universal Geometric Learning}}},
author = {Dym, Nadav and Gortler, Steven J.},
date = {2022-05-05},
- number = {arXiv:2205.02956},
eprint = {2205.02956},
eprinttype = {arxiv},
eprintclass = {cs, math},
@@ -2485,15 +2721,14 @@
title = {Accelerating {{Equilibration}} in {{First-Principles Molecular Dynamics}} with {{Orbital-Free Density Functional Theory}}},
author = {Fiedler, Lenz and Moldabekov, Zhandos A. and Shao, Xuecheng and Jiang, Kaili and Dornheim, Tobias and Pavanello, Michele and Cangi, Attila},
date = {2022-09-02},
- number = {arXiv:2206.03754},
- eprint = {arXiv:2206.03754},
+ eprint = {2206.03754},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2206.03754},
url = {http://arxiv.org/abs/2206.03754},
urldate = {2023-02-15},
abstract = {We introduce a practical hybrid approach that combines orbital-free density functional theory (DFT) with Kohn-Sham DFT for speeding up first-principles molecular dynamics simulations. Equilibrated ionic configurations are generated using orbital-free DFT for subsequent Kohn-Sham DFT molecular dynamics. This leads to a massive reduction of the simulation time without any sacrifice in accuracy. We assess this finding across systems of different sizes and temperature, up to the warm dense matter regime. To that end, we use the cosine distance between the time series of radial distribution functions representing the ionic configurations. Likewise, we show that the equilibrated ionic configurations from this hybrid approach significantly enhance the accuracy of machine-learning models that replace Kohn-Sham DFT. Our hybrid scheme enables systematic first-principles simulations of warm dense matter that are otherwise hampered by the large numbers of atoms and the prevalent high temperatures. Moreover, our finding provides an additional motivation for developing kinetic and noninteracting free energy functionals for orbital-free DFT.},
pubstate = {preprint},
- keywords = {/unread},
file = {/Users/wasmer/Nextcloud/Zotero/Fiedler et al_2022_Accelerating Equilibration in First-Principles Molecular Dynamics with.pdf;/Users/wasmer/Zotero/storage/TA7XVJUP/2206.html}
}
@@ -2515,9 +2750,9 @@
title = {A {{Deep Dive}} into {{Machine Learning Density Functional Theory}} for {{Materials Science}} and {{Chemistry}}},
author = {Fiedler, Lenz and Shah, Karan and Bussmann, Michael and Cangi, Attila},
date = {2022-02-25},
- number = {arXiv:2110.00997},
- eprint = {arXiv:2110.00997},
+ eprint = {2110.00997},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2110.00997},
url = {http://arxiv.org/abs/2110.00997},
urldate = {2023-02-15},
@@ -2549,9 +2784,9 @@
title = {Predicting Electronic Structures at Any Length Scale with Machine Learning},
author = {Fiedler, Lenz and Modine, Normand A. and Schmerler, Steve and Vogel, Dayton J. and Popoola, Gabriel A. and Thompson, Aidan P. and Rajamanickam, Sivasankaran and Cangi, Attila},
date = {2022-12-08},
- number = {arXiv:2210.11343},
- eprint = {arXiv:2210.11343},
+ eprint = {2210.11343},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2210.11343},
url = {http://arxiv.org/abs/2210.11343},
urldate = {2023-02-15},
@@ -2577,7 +2812,7 @@
url = {http://arxiv.org/abs/2202.09186},
urldate = {2023-02-15},
abstract = {A myriad of phenomena in materials science and chemistry rely on quantum-level simulations of the electronic structure in matter. While moving to larger length and time scales has been a pressing issue for decades, such large-scale electronic structure calculations are still challenging despite modern software approaches and advances in high-performance computing. The silver lining in this regard is the use of machine learning to accelerate electronic structure calculations -- this line of research has recently gained growing attention. The grand challenge therein is finding a suitable machine-learning model during a process called hyperparameter optimization. This, however, causes a massive computational overhead in addition to that of data generation. We accelerate the construction of neural network models by roughly two orders of magnitude by circumventing excessive training during the hyperparameter optimization phase. We demonstrate our workflow for Kohn-Sham density functional theory, the most popular computational method in materials science and chemistry.},
- keywords = {_tablet,/unread},
+ keywords = {_tablet},
file = {/Users/wasmer/Nextcloud/Zotero/Fiedler et al_2022_Training-free hyperparameter optimization of neural networks for electronic.pdf;/Users/wasmer/Zotero/storage/6BKNM2VX/2202.html}
}
@@ -2602,9 +2837,9 @@
title = {Linear {{Jacobi-Legendre}} Expansion of the Charge Density for Machine Learning-Accelerated Electronic Structure Calculations},
author = {Focassio, Bruno and Domina, Michelangelo and Patil, Urvesh and Fazzio, Adalberto and Sanvito, Stefano},
date = {2023-01-31},
- number = {arXiv:2301.13550},
- eprint = {arXiv:2301.13550},
+ eprint = {2301.13550},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2301.13550},
url = {http://arxiv.org/abs/2301.13550},
urldate = {2023-02-23},
@@ -2618,7 +2853,6 @@
title = {Topology, {{Entanglement}}, and {{Strong Correlations}}},
author = {Foulkes, W. M. C. and Drautz, Ralf},
date = {2020},
- series = {Lecture {{Notes}} of the {{Autumn School}} on {{Correlated Electrons}}},
number = {FZJ-2020-03083},
institution = {{Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag}},
url = {https://juser.fz-juelich.de/record/884084/},
@@ -2633,12 +2867,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Foulkes_Drautz_2020_Topology, Entanglement, and Strong Correlations.pdf;/Users/wasmer/Zotero/storage/WLIE37SZ/884084.html}
}
+@inproceedings{foxConcentricSphericalNeural2022,
+ title = {Concentric {{Spherical Neural Network}} for {{3D Representation Learning}}},
+ booktitle = {2022 {{International Joint Conference}} on {{Neural Networks}} ({{IJCNN}})},
+ author = {Fox, James and Zhao, Bo and family=Rio, given=Beatriz Gonzalez, prefix=del, useprefix=true and Rajamanickam, Sivasankaran and Ramprasad, Rampi and Song, Le},
+ date = {2022-07},
+ pages = {1--8},
+ issn = {2161-4407},
+ doi = {10.1109/IJCNN55064.2022.9892358},
+ abstract = {Learning 3D representations of point clouds that generalize well to arbitrary orientations is a challenge of practical importance in domains ranging from computer vision to molecular modeling. The proposed approach uses a concentric spherical spatial representation, formed by nesting spheres discretized the icosahedral grid, as the basis for structured learning over point clouds. We propose rotationally equivariant convolutions for learning over the concentric spherical grid, which are incorporated into a novel architecture for representation learning that is robust to general rotations in 3D. We demonstrate the effectiveness and extensibility of our approach to problems in different domains, such as 3D shape recognition and predicting fundamental properties of molecular systems.},
+ eventtitle = {2022 {{International Joint Conference}} on {{Neural Networks}} ({{IJCNN}})},
+ keywords = {AML,convolution,CSNN,equivariant,General ML,GNN,library,ML,ML-DFT,ML-ESM,NN,original publication,point cloud compression,point cloud data,prediction of DOS,representation learning,spherical convolution,spherical NN},
+ file = {/Users/wasmer/Nextcloud/Zotero/Fox et al_2022_Concentric Spherical Neural Network for 3D Representation Learning.pdf;/Users/wasmer/Zotero/storage/YBYXAFZ3/9892358.html}
+}
+
@unpublished{frankDetectInteractionsThat2021,
title = {Detect the {{Interactions}} That {{Matter}} in {{Matter}}: {{Geometric Attention}} for {{Many-Body Systems}}},
shorttitle = {Detect the {{Interactions}} That {{Matter}} in {{Matter}}},
author = {Frank, Thorben and Chmiela, Stefan},
date = {2021-09-06},
- number = {arXiv:2106.02549},
eprint = {2106.02549},
eprinttype = {arxiv},
eprintclass = {physics},
@@ -2651,6 +2898,23 @@
file = {/Users/wasmer/Nextcloud/Zotero/Frank_Chmiela_2021_Detect the Interactions that Matter in Matter.pdf;/Users/wasmer/Zotero/storage/7QC4UBJN/2106.html}
}
+@online{frankSo3kratesEquivariantAttention2023,
+ title = {So3krates: {{Equivariant}} Attention for Interactions on Arbitrary Length-Scales in Molecular Systems},
+ shorttitle = {So3krates},
+ author = {Frank, J. Thorben and Unke, Oliver T. and Müller, Klaus-Robert},
+ date = {2023-01-09},
+ eprint = {2205.14276},
+ eprinttype = {arxiv},
+ eprintclass = {cs},
+ doi = {10.48550/arXiv.2205.14276},
+ url = {http://arxiv.org/abs/2205.14276},
+ urldate = {2023-04-04},
+ abstract = {The application of machine learning methods in quantum chemistry has enabled the study of numerous chemical phenomena, which are computationally intractable with traditional ab-initio methods. However, some quantum mechanical properties of molecules and materials depend on non-local electronic effects, which are often neglected due to the difficulty of modeling them efficiently. This work proposes a modified attention mechanism adapted to the underlying physics, which allows to recover the relevant non-local effects. Namely, we introduce spherical harmonic coordinates (SPHCs) to reflect higher-order geometric information for each atom in a molecule, enabling a non-local formulation of attention in the SPHC space. Our proposed model So3krates - a self-attention based message passing neural network - uncouples geometric information from atomic features, making them independently amenable to attention mechanisms. Thereby we construct spherical filters, which extend the concept of continuous filters in Euclidean space to SPHC space and serve as foundation for a spherical self-attention mechanism. We show that in contrast to other published methods, So3krates is able to describe non-local quantum mechanical effects over arbitrary length scales. Further, we find evidence that the inclusion of higher-order geometric correlations increases data efficiency and improves generalization. So3krates matches or exceeds state-of-the-art performance on popular benchmarks, notably, requiring a significantly lower number of parameters (0.25 - 0.4x) while at the same time giving a substantial speedup (6 - 14x for training and 2 - 11x for inference) compared to other models.},
+ pubstate = {preprint},
+ keywords = {AML,attention,equivariant,Euclidean space,FLAX,GDL,invariance,JAX,library,long-range interaction,ML,ML-FF,molecules,MPNN,NequIP,original publication,QM7-X,SchNet,sGDML,SO(3),spherical harmonic coordinates,SpookyNet,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Frank et al_2023_So3krates.pdf;/Users/wasmer/Zotero/storage/9GZJ7VNS/2205.html}
+}
+
@article{frauxChemiscopeInteractiveStructureproperty2020,
title = {Chemiscope: Interactive Structure-Property Explorer for Materials and Molecules},
shorttitle = {Chemiscope},
@@ -2763,9 +3027,9 @@
shorttitle = {{{SE}}(3)-{{Transformers}}},
author = {Fuchs, Fabian B. and Worrall, Daniel E. and Fischer, Volker and Welling, Max},
date = {2020-11-24},
- number = {arXiv:2006.10503},
- eprint = {arXiv:2006.10503},
+ eprint = {2006.10503},
eprinttype = {arxiv},
+ eprintclass = {cs, stat},
doi = {10.48550/arXiv.2006.10503},
url = {http://arxiv.org/abs/2006.10503},
urldate = {2022-10-03},
@@ -2775,6 +3039,41 @@
file = {/Users/wasmer/Nextcloud/Zotero/Fuchs et al_2020_SE(3)-Transformers.pdf;/Users/wasmer/Zotero/storage/UMVV286P/2006.html}
}
+@online{fuForcesAreNot2022,
+ title = {Forces Are Not {{Enough}}: {{Benchmark}} and {{Critical Evaluation}} for {{Machine Learning Force Fields}} with {{Molecular Simulations}}},
+ shorttitle = {Forces Are Not {{Enough}}},
+ author = {Fu, Xiang and Wu, Zhenghao and Wang, Wujie and Xie, Tian and Keten, Sinan and Gomez-Bombarelli, Rafael and Jaakkola, Tommi},
+ date = {2022-10-13},
+ eprint = {2210.07237},
+ eprinttype = {arxiv},
+ eprintclass = {physics},
+ doi = {10.48550/arXiv.2210.07237},
+ url = {http://arxiv.org/abs/2210.07237},
+ urldate = {2023-04-03},
+ abstract = {Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for ML MD simulation. We curate representative MD systems, including water, organic molecules, peptide, and materials, and design evaluation metrics corresponding to the scientific objectives of respective systems. We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics. We demonstrate when and how selected SOTA methods fail, along with offering directions for further improvement. Specifically, we identify stability as a key metric for ML models to improve. Our benchmark suite comes with a comprehensive open-source codebase for training and simulation with ML FFs to facilitate further work.},
+ pubstate = {preprint},
+ keywords = {AML,benchmarking,DimeNet,equivariant,GemNet,invariance,MD,MD17,Microsoft Research,ML,ML-FF,MLP,NequIP,PES,SchNet},
+ file = {/Users/wasmer/Nextcloud/Zotero/Fu et al_2022_Forces are not Enough.pdf;/Users/wasmer/Zotero/storage/2GZERUJD/2210.html}
+}
+
+@article{fukushimaAutomaticExhaustiveCalculations2022,
+ title = {Automatic Exhaustive Calculations of Large Material Space by {{Korringa-Kohn-Rostoker}} Coherent Potential Approximation Method Applied to Equiatomic Quaternary High Entropy Alloys},
+ author = {Fukushima, T. and Akai, H. and Chikyow, T. and Kino, H.},
+ date = {2022-02-17},
+ journaltitle = {Physical Review Materials},
+ shortjournal = {Phys. Rev. Mater.},
+ volume = {6},
+ number = {2},
+ pages = {023802},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevMaterials.6.023802},
+ url = {https://link.aps.org/doi/10.1103/PhysRevMaterials.6.023802},
+ urldate = {2023-04-04},
+ abstract = {Automatic exhaustive exploration of a large material space by high-performance supercomputers is crucial for developing new functional materials. We demonstrated the efficiency of high-throughput calculations using the all-electron Korringa-Kohn-Rostoker coherent potential approximation method with the density functional theory for the large material space consisting of quaternary high entropy alloys, which are nonstoichiometric and substitutionally disordered materials. The exhaustive calculations were performed for 147 630 systems based on the AkaiKKR program package and supercomputer Fugaku, where the numerical parameters and self-consistent convergence are automatically controlled. The large material database including the total energies, magnetization, Curie temperature, and residual resistivity was constructed by our calculations. We used frequent itemset mining to identify the characteristics of parcels in magnetization and Curie temperature space. We also identified the elements that enhance the magnetization and Curie temperature and clarified the rough dependence of the elements through regression modeling of the residual resistivity.},
+ keywords = {/unread,CPA,HTC,KKR},
+ file = {/Users/wasmer/Nextcloud/Zotero/Fukushima et al_2022_Automatic exhaustive calculations of large material space by.pdf;/Users/wasmer/Zotero/storage/VNUQ6LGT/PhysRevMaterials.6.html}
+}
+
@article{fungPhysicallyInformedMachine2022,
title = {Physically {{Informed Machine Learning Prediction}} of {{Electronic Density}} of {{States}}},
author = {Fung, Victor and Ganesh, P. and Sumpter, Bobby G.},
@@ -2819,13 +3118,34 @@
keywords = {OO,Reusability,software engineering,Software patterns}
}
+@article{gaoSelfconsistentDeterminationLongrange2022,
+ title = {Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials},
+ author = {Gao, Ang and Remsing, Richard C.},
+ date = {2022-03-23},
+ journaltitle = {Nature Communications},
+ shortjournal = {Nat Commun},
+ volume = {13},
+ number = {1},
+ pages = {1572},
+ publisher = {{Nature Publishing Group}},
+ issn = {2041-1723},
+ doi = {10.1038/s41467-022-29243-2},
+ url = {https://www.nature.com/articles/s41467-022-29243-2},
+ urldate = {2023-04-04},
+ abstract = {Machine learning has the potential to revolutionize the field of molecular simulation through the development of efficient and accurate models of interatomic interactions. Neural networks can model interactions with the accuracy of quantum mechanics-based calculations, but with a fraction of the cost, enabling simulations of large systems over long timescales. However, implicit in the construction of neural network potentials is an assumption of locality, wherein atomic arrangements on the nanometer-scale are used to learn interatomic interactions. Because of this assumption, the resulting neural network models cannot describe long-range interactions that play critical roles in dielectric screening and chemical reactivity. Here, we address this issue by introducing the self-consistent field neural network — a general approach for learning the long-range response of molecular systems in neural network potentials that relies on a physically meaningful separation of the interatomic interactions — and demonstrate its utility by modeling liquid water with and without applied fields.},
+ issue = {1},
+ langid = {english},
+ keywords = {/unread,AML,electrostatic interaction,long-range interaction,MD,ML,MLP,NN,SCF,SCFNN},
+ file = {/Users/wasmer/Nextcloud/Zotero/Gao_Remsing_2022_Self-consistent determination of long-range electrostatics in neural network.pdf}
+}
+
@online{gardnerSyntheticDataEnable2022,
title = {Synthetic Data Enable Experiments in Atomistic Machine Learning},
author = {Gardner, John L. A. and Beaulieu, Zoé Faure and Deringer, Volker L.},
date = {2022-11-29},
- number = {arXiv:2211.16443},
- eprint = {arXiv:2211.16443},
+ eprint = {2211.16443},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2211.16443},
url = {http://arxiv.org/abs/2211.16443},
urldate = {2022-12-29},
@@ -2839,9 +3159,9 @@
title = {Synthetic Data Enable Experiments in Atomistic Machine Learning},
author = {Gardner, John L. A. and Beaulieu, Zoé Faure and Deringer, Volker L.},
date = {2022-11-29},
- number = {arXiv:2211.16443},
- eprint = {arXiv:2211.16443},
+ eprint = {2211.16443},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2211.16443},
url = {http://arxiv.org/abs/2211.16443},
urldate = {2023-03-01},
@@ -2873,9 +3193,9 @@
title = {Directional {{Message Passing}} for {{Molecular Graphs}}},
author = {Gasteiger, Johannes and Groß, Janek and Günnemann, Stephan},
date = {2022-04-05},
- number = {arXiv:2003.03123},
- eprint = {arXiv:2003.03123},
+ eprint = {2003.03123},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.2003.03123},
url = {http://arxiv.org/abs/2003.03123},
urldate = {2022-10-03},
@@ -2889,9 +3209,9 @@
title = {Directional {{Message Passing}} on {{Molecular Graphs}} via {{Synthetic Coordinates}}},
author = {Gasteiger, Johannes and Yeshwanth, Chandan and Günnemann, Stephan},
date = {2022-04-05},
- number = {arXiv:2111.04718},
- eprint = {arXiv:2111.04718},
+ eprint = {2111.04718},
eprinttype = {arxiv},
+ eprintclass = {physics, q-bio},
doi = {10.48550/arXiv.2111.04718},
url = {http://arxiv.org/abs/2111.04718},
urldate = {2022-10-03},
@@ -2905,9 +3225,9 @@
title = {Fast and {{Uncertainty-Aware Directional Message Passing}} for {{Non-Equilibrium Molecules}}},
author = {Gasteiger, Johannes and Giri, Shankari and Margraf, Johannes T. and Günnemann, Stephan},
date = {2022-04-05},
- number = {arXiv:2011.14115},
- eprint = {arXiv:2011.14115},
+ eprint = {2011.14115},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2011.14115},
url = {http://arxiv.org/abs/2011.14115},
urldate = {2022-10-03},
@@ -2922,9 +3242,9 @@
shorttitle = {{{GemNet}}},
author = {Gasteiger, Johannes and Becker, Florian and Günnemann, Stephan},
date = {2022-04-05},
- number = {arXiv:2106.08903},
- eprint = {arXiv:2106.08903},
+ eprint = {2106.08903},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.2106.08903},
url = {http://arxiv.org/abs/2106.08903},
urldate = {2022-10-03},
@@ -2979,9 +3299,9 @@
shorttitle = {E3nn},
author = {Geiger, Mario and Smidt, Tess},
date = {2022-07-18},
- number = {arXiv:2207.09453},
- eprint = {arXiv:2207.09453},
+ eprint = {2207.09453},
eprinttype = {arxiv},
+ eprintclass = {cs},
doi = {10.48550/arXiv.2207.09453},
url = {http://arxiv.org/abs/2207.09453},
urldate = {2022-08-21},
@@ -3010,9 +3330,9 @@
shorttitle = {Gold-Standard Solutions to the {{Schr}}\textbackslash "odinger Equation Using Deep Learning},
author = {Gerard, Leon and Scherbela, Michael and Marquetand, Philipp and Grohs, Philipp},
date = {2022-05-31},
- number = {arXiv:2205.09438},
- eprint = {arXiv:2205.09438},
+ eprint = {2205.09438},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2205.09438},
url = {http://arxiv.org/abs/2205.09438},
urldate = {2022-08-16},
@@ -3038,6 +3358,24 @@
file = {/home/johannes/Books/machine_learning/general_practice/Géron_2019_Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow.pdf}
}
+@article{ghasemiInteratomicPotentialsIonic2015,
+ title = {Interatomic Potentials for Ionic Systems with Density Functional Accuracy Based on Charge Densities Obtained by a Neural Network},
+ author = {Ghasemi, S. Alireza and Hofstetter, Albert and Saha, Santanu and Goedecker, Stefan},
+ date = {2015-07-30},
+ journaltitle = {Physical Review B},
+ shortjournal = {Phys. Rev. B},
+ volume = {92},
+ number = {4},
+ pages = {045131},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevB.92.045131},
+ url = {https://link.aps.org/doi/10.1103/PhysRevB.92.045131},
+ urldate = {2023-04-04},
+ abstract = {Based on an analysis of the short-range chemical environment of each atom in a system, standard machine-learning-based approaches to the construction of interatomic potentials aim at determining directly the central quantity, which is the total energy. This prevents, for instance, an accurate description of the energetics of systems in which long-range charge transfer or ionization is important. We propose therefore not to target directly with machine-learning methods the total energy but an intermediate physical quantity, namely, the charge density, which then in turn allows us to determine the total energy. By allowing the electronic charge to distribute itself in an optimal way over the system, we can describe not only neutral but also ionized systems with unprecedented accuracy. We demonstrate the power of our approach for both neutral and ionized NaCl clusters where charge redistribution plays a decisive role for the energetics. We are able to obtain chemical accuracy, i.e., errors of less than a millihartree per atom compared to the reference density functional results for a huge data set of configurations with large structural variety. The introduction of physically motivated quantities which are determined by the short-range atomic environment via a neural network also leads to an increased stability of the machine-learning process and transferability of the potential.},
+ keywords = {AML,BigDFT,charge equilibration,charge transfer,electronegativity,electrostatic interaction,ionic systems,LDA,long-range interaction,ML,ML-DFT,MLP,NN,NNP,PES,prediction of electron density,prediction of electronegativity},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ghasemi et al_2015_Interatomic potentials for ionic systems with density functional accuracy based.pdf;/Users/wasmer/Zotero/storage/HYUBBIPY/PhysRevB.92.html}
+}
+
@article{ghiringhelliAItoolkitDevelopShare2021,
title = {An {{AI-toolkit}} to Develop and Share Research into New Materials},
author = {Ghiringhelli, Luca M.},
@@ -3102,9 +3440,9 @@
title = {Classical and Quantum Machine Learning Applications in Spintronics},
author = {Ghosh, Kumar and Ghosh, Sumit},
date = {2022-07-26},
- number = {arXiv:2207.12837},
- eprint = {arXiv:2207.12837},
+ eprint = {2207.12837},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics, physics:quant-ph},
doi = {10.48550/arXiv.2207.12837},
url = {http://arxiv.org/abs/2207.12837},
urldate = {2022-10-28},
@@ -3114,19 +3452,37 @@
file = {/Users/wasmer/Nextcloud/Zotero/Ghosh_Ghosh_2022_Classical and quantum machine learning applications in spintronics.pdf;/Users/wasmer/Zotero/storage/FEUD8XZQ/2207.html}
}
+@article{ghoshShortrangeOrderPhase2022,
+ title = {Short-Range Order and Phase Stability of {{CrCoNi}} Explored with Machine Learning Potentials},
+ author = {Ghosh, Sheuly and Sotskov, Vadim and Shapeev, Alexander V. and Neugebauer, Jörg and Körmann, Fritz},
+ date = {2022-11-30},
+ journaltitle = {Physical Review Materials},
+ shortjournal = {Phys. Rev. Mater.},
+ volume = {6},
+ number = {11},
+ pages = {113804},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevMaterials.6.113804},
+ url = {https://link.aps.org/doi/10.1103/PhysRevMaterials.6.113804},
+ urldate = {2023-04-04},
+ abstract = {We present an analysis of temperature-dependent atomic short-range ordering and phase stability of the face-centered cubic CrCoNi medium-entropy alloy employing a combination of ab initio calculations and on-lattice machine learning interatomic potentials. Temperature-dependent properties are studied with canonical Monte Carlo simulations. At around 975 K a phase transition into an ordered Cr(Ni,Co)2 phase (MoPt2-type) is found. This hitherto not reported state has an ordering energy twice as large than the ordered structures previously suggested. We show that magnetism is not responsible for the observed chemical ordering.},
+ keywords = {alloys,AML,disordered,LRP,magnetism,MC,ML,MLP,n-ary alloys,PBE,prediction of energy,spin-dependent,spin-polarized,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ghosh et al_2022_Short-range order and phase stability of CrCoNi explored with machine learning.pdf;/Users/wasmer/Zotero/storage/YXSSR3DU/PhysRevMaterials.6.html}
+}
+
@online{gilliganRulefreeWorkflowAutomated2023,
title = {A Rule-Free Workflow for the Automated Generation of Databases from Scientific Literature},
author = {Gilligan, Luke P. J. and Cobelli, Matteo and Taufour, Valentin and Sanvito, Stefano},
date = {2023-01-27},
- number = {arXiv:2301.11689},
- eprint = {arXiv:2301.11689},
+ eprint = {2301.11689},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2301.11689},
url = {http://arxiv.org/abs/2301.11689},
urldate = {2023-02-23},
abstract = {In recent times, transformer networks have achieved state-of-the-art performance in a wide range of natural language processing tasks. Here we present a workflow based on the fine-tuning of BERT models for different downstream tasks, which results in the automated extraction of structured information from unstructured natural language in scientific literature. Contrary to other methods for the automated extraction of structured compound-property relations from similar sources, our workflow does not rely on the definition of intricate grammar rules. Hence, it can be adapted to a new task without requiring extensive implementation efforts and knowledge. We test the data extraction performance by automatically generating a database of compounds and their associated Curie temperatures. This is compared with a manually curated database and one obtained with the state-of-the-art rule-based method. Finally, in order to demonstrate that the automatically extracted database can be used in a material-design workflow, we employ it to construct a machine-learning model predicting the Curie temperature based on a compound's chemical composition. This is quantitatively tested and compared with the best model constructed on manually-extracted data.},
pubstate = {preprint},
- keywords = {_tablet,/unread,Condensed Matter - Materials Science,Physics - Computational Physics,Physics - Data Analysis; Statistics and Probability},
+ keywords = {_tablet,BERT,data mining,database generation,literature analysis,LLM,materials},
file = {/Users/wasmer/Nextcloud/Zotero/Gilligan et al_2023_A rule-free workflow for the automated generation of databases from scientific.pdf;/Users/wasmer/Zotero/storage/W8WDMBDK/2301.html}
}
@@ -3134,9 +3490,9 @@
title = {Neural {{Message Passing}} for {{Quantum Chemistry}}},
author = {Gilmer, Justin and Schoenholz, Samuel S. and Riley, Patrick F. and Vinyals, Oriol and Dahl, George E.},
date = {2017-06-12},
- number = {arXiv:1704.01212},
- eprint = {arXiv:1704.01212},
+ eprint = {1704.01212},
eprinttype = {arxiv},
+ eprintclass = {cs},
doi = {10.48550/arXiv.1704.01212},
url = {http://arxiv.org/abs/1704.01212},
urldate = {2022-10-03},
@@ -3220,7 +3576,7 @@
doi = {10.1093/pnasnexus/pgac039},
url = {https://www.pnas.org/doi/full/10.1093/pnasnexus/pgac039},
urldate = {2022-07-02},
- keywords = {ACSF,descriptor comparison,descriptors,dimensionality reduction,GPR,information imbalance,MD,ML,SOAP},
+ keywords = {ACSF,chemical species scaling problem,descriptor comparison,descriptors,dimensionality reduction,GPR,information imbalance,MD,ML,SOAP},
file = {/Users/wasmer/Nextcloud/Zotero/Glielmo et al_2022_Ranking the information content of distance measures.pdf}
}
@@ -3269,9 +3625,9 @@
title = {Rapid {{Discovery}} of {{Stable Materials}} by {{Coordinate-free Coarse Graining}}},
author = {Goodall, Rhys E. A. and Parackal, Abhijith S. and Faber, Felix A. and Armiento, Rickard and Lee, Alpha A.},
date = {2022-03-15},
- number = {arXiv:2106.11132},
- eprint = {arXiv:2106.11132},
+ eprint = {2106.11132},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2106.11132},
url = {http://arxiv.org/abs/2106.11132},
urldate = {2022-10-03},
@@ -3357,15 +3713,15 @@
title = {Electronic-Structure Properties from Atom-Centered Predictions of the Electron Density},
author = {Grisafi, Andrea and Lewis, Alan M. and Rossi, Mariana and Ceriotti, Michele},
date = {2022-06-28},
- number = {arXiv:2206.14087},
- eprint = {arXiv:2206.14087},
+ eprint = {2206.14087},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics, stat},
doi = {10.48550/arXiv.2206.14087},
url = {http://arxiv.org/abs/2206.14087},
urldate = {2022-07-02},
abstract = {The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to represent the scalar field using a multi-centered atomic basis analogous to that routinely used in density fitting approximations. However, the non-orthogonality of the basis poses challenges for the learning exercise, as it requires accounting for all the atomic density components at once. We devise a gradient-based approach to directly minimize the loss function of the regression problem in an optimized and highly sparse feature space. In so doing, we overcome the limitations associated with adopting an atom-centered model to learn the electron density over arbitrarily complex datasets, obtaining extremely accurate predictions. The enhanced framework is tested on 32-molecule periodic cells of liquid water, presenting enough complexity to require an optimal balance between accuracy and computational efficiency. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom with respect to the reference density functional calculations. Finally, we test our method on the highly heterogeneous QM9 benchmark dataset, showing that a small fraction of the training data is enough to derive ground-state total energies within chemical accuracy.},
pubstate = {preprint},
- keywords = {_tablet,DFT,dimensionality reduction,equivariant,ML-DFT,ML-ESM,molecules,molecules & solids,prediction of electron density,QM9,SALTED,SOAP,solids},
+ keywords = {_tablet,DFT,dimensionality reduction,equivariant,lambda-SOAP,ML-DFT,ML-ESM,molecules,molecules & solids,prediction of electron density,QM9,RKHS,SA-GPR,SALTED,SOAP,solids},
file = {/Users/wasmer/Nextcloud/Zotero/Grisafi et al_2022_Electronic-structure properties from atom-centered predictions of the electron.pdf;/Users/wasmer/Zotero/storage/QPHBS33I/2206.html}
}
@@ -3381,7 +3737,7 @@
url = {https://doi.org/10.1021/acs.jctc.2c00850},
urldate = {2023-01-25},
abstract = {The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to represent the scalar field using a multicentered atomic basis analogous to that routinely used in density fitting approximations. However, the nonorthogonality of the basis poses challenges for the learning exercise, as it requires accounting for all the atomic density components at once. We devise a gradient-based approach to directly minimize the loss function of the regression problem in an optimized and highly sparse feature space. In so doing, we overcome the limitations associated with adopting an atom-centered model to learn the electron density over arbitrarily complex data sets, obtaining very accurate predictions using a comparatively small training set. The enhanced framework is tested on 32-molecule periodic cells of liquid water, presenting enough complexity to require an optimal balance between accuracy and computational efficiency. We show that starting from the predicted density a single Kohn–Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom with respect to the reference density functional calculations. Finally, we test our method on the highly heterogeneous QM9 benchmark data set, showing that a small fraction of the training data is enough to derive ground-state total energies within chemical accuracy.},
- keywords = {DFT,dimensionality reduction,equivariant,ML-DFT,ML-ESM,molecules,molecules & solids,prediction of electron density,QM9,SALTED,SOAP,solids},
+ keywords = {DFT,dimensionality reduction,equivariant,lambda-SOAP,ML-DFT,ML-ESM,molecules,molecules & solids,prediction of electron density,QM9,RKHS,SA-GPR,SALTED,SOAP,solids},
file = {/Users/wasmer/Nextcloud/Zotero/Grisafi et al_2022_Electronic-Structure Properties from Atom-Centered Predictions of the Electron.pdf;/Users/wasmer/Zotero/storage/29HAHUDS/acs.jctc.html}
}
@@ -3404,6 +3760,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Grisafi_Ceriotti_2019_Incorporating long-range physics in atomic-scale machine learning.pdf}
}
+@article{grisafiIncorporatingLongrangePhysics2019a,
+ title = {Incorporating Long-Range Physics in Atomic-Scale Machine Learning},
+ author = {Grisafi, Andrea and Ceriotti, Michele},
+ date = {2019-11-28},
+ journaltitle = {The Journal of Chemical Physics},
+ shortjournal = {J. Chem. Phys.},
+ volume = {151},
+ number = {20},
+ pages = {204105},
+ publisher = {{American Institute of Physics}},
+ issn = {0021-9606},
+ doi = {10.1063/1.5128375},
+ url = {https://aip.scitation.org/doi/full/10.1063/1.5128375},
+ urldate = {2023-04-04},
+ abstract = {The most successful and popular machine learning models of atomic-scale properties derive their transferability from a locality ansatz. The properties of a large molecule or a bulk material are written as a sum over contributions that depend on the configurations within finite atom-centered environments. The obvious downside of this approach is that it cannot capture nonlocal, nonadditive effects such as those arising due to long-range electrostatics or quantum interference. We propose a solution to this problem by introducing nonlocal representations of the system, which are remapped as feature vectors that are defined locally and are equivariant in O(3). We consider, in particular, one form that has the same asymptotic behavior as the electrostatic potential. We demonstrate that this framework can capture nonlocal, long-range physics by building a model for the electrostatic energy of randomly distributed point-charges, for the unrelaxed binding curves of charged organic molecular dimers, and for the electronic dielectric response of liquid water. By combining a representation of the system that is sensitive to long-range correlations with the transferability of an atom-centered additive model, this method outperforms current state-of-the-art machine-learning schemes and provides a conceptual framework to incorporate nonlocal physics into atomistic machine learning.},
+ keywords = {ACDC,AML,electrostatic interaction,equivariant,library,LODE,long-range interaction,ML,original publication,SA-GPR,SOAP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Grisafi_Ceriotti_2019_Incorporating long-range physics in atomic-scale machine learning2.pdf;/Users/wasmer/Nextcloud/Zotero/Grisafi_Ceriotti_2019_Incorporating long-range physics in atomic-scale machine learning3.pdf}
+}
+
@article{grisafiMultiscaleApproachPrediction2021,
title = {Multi-Scale Approach for the Prediction of Atomic Scale Properties},
author = {Grisafi, Andrea and Nigam, Jigyasa and Ceriotti, Michele},
@@ -3494,9 +3869,9 @@
title = {Pen and {{Paper Exercises}} in {{Machine Learning}}},
author = {Gutmann, Michael U.},
date = {2022-06-27},
- number = {arXiv:2206.13446},
- eprint = {arXiv:2206.13446},
+ eprint = {2206.13446},
eprinttype = {arxiv},
+ eprintclass = {cs, stat},
doi = {10.48550/arXiv.2206.13446},
url = {http://arxiv.org/abs/2206.13446},
urldate = {2022-06-29},
@@ -3623,7 +3998,7 @@
title = {Structure-Property Maps with {{Kernel}} Principal Covariates Regression},
author = {Helfrecht, Benjamin A. and Cersonsky, Rose K. and Fraux, Guillaume and Ceriotti, Michele},
date = {2020-11},
- shortjournal = {Mach. Learn.: Sci. Technol.},
+ journaltitle = {Mach. Learn.: Sci. Technol.},
volume = {1},
number = {4},
pages = {045021},
@@ -3991,6 +4366,26 @@
file = {/Users/wasmer/Zotero/storage/WLWNEY4Q/1.html}
}
+@article{ismail-beigiNewAlgebraicFormulation2000,
+ title = {New {{Algebraic Formulation}} of {{Density Functional Calculation}}},
+ author = {Ismail-Beigi, Sohrab and Arias, T. A.},
+ date = {2000-06},
+ journaltitle = {Computer Physics Communications},
+ shortjournal = {Computer Physics Communications},
+ volume = {128},
+ number = {1-2},
+ eprint = {cond-mat/9909130},
+ eprinttype = {arxiv},
+ pages = {1--45},
+ issn = {00104655},
+ doi = {10.1016/S0010-4655(00)00072-2},
+ url = {http://arxiv.org/abs/cond-mat/9909130},
+ urldate = {2023-04-07},
+ abstract = {This article addresses a fundamental problem faced by the ab initio community: the lack of an effective formalism for the rapid exploration and exchange of new methods. To rectify this, we introduce a novel, basis-set independent, matrix-based formulation of generalized density functional theories which reduces the development, implementation, and dissemination of new ab initio techniques to the derivation and transcription of a few lines of algebra. This new framework enables us to concisely demystify the inner workings of fully functional, highly efficient modern ab initio codes and to give complete instructions for the construction of such for calculations employing arbitrary basis sets. Within this framework, we also discuss in full detail a variety of leading-edge ab initio techniques, minimization algorithms, and highly efficient computational kernels for use with scalar as well as shared and distributed-memory supercomputer architectures.},
+ keywords = {Condensed Matter - Materials Science},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ismail-Beigi_Arias_2000_New Algebraic Formulation of Density Functional Calculation.pdf;/Users/wasmer/Zotero/storage/JRMEXIH4/9909130.html}
+}
+
@article{jablonkaBigDataSciencePorous2020,
title = {Big-{{Data Science}} in {{Porous Materials}}: {{Materials Genomics}} and {{Machine Learning}}},
shorttitle = {Big-{{Data Science}} in {{Porous Materials}}},
@@ -4157,9 +4552,9 @@
shorttitle = {{{DeepDFT}}},
author = {Jørgensen, Peter Bjørn and Bhowmik, Arghya},
date = {2020-11-04},
- number = {arXiv:2011.03346},
- eprint = {arXiv:2011.03346},
+ eprint = {2011.03346},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2011.03346},
url = {http://arxiv.org/abs/2011.03346},
urldate = {2022-07-10},
@@ -4169,13 +4564,34 @@
file = {/Users/wasmer/Nextcloud/Zotero/Jørgensen_Bhowmik_2020_DeepDFT.pdf;/Users/wasmer/Zotero/storage/QXJKV745/2011.html}
}
+@article{jorgensenEquivariantGraphNeural2022,
+ title = {Equivariant Graph Neural Networks for Fast Electron Density Estimation of Molecules, Liquids, and Solids},
+ author = {Jørgensen, Peter Bjørn and Bhowmik, Arghya},
+ date = {2022-08-23},
+ journaltitle = {npj Computational Materials},
+ shortjournal = {npj Comput Mater},
+ volume = {8},
+ number = {1},
+ pages = {1--10},
+ publisher = {{Nature Publishing Group}},
+ issn = {2057-3960},
+ doi = {10.1038/s41524-022-00863-y},
+ url = {https://www.nature.com/articles/s41524-022-00863-y},
+ urldate = {2023-04-14},
+ abstract = {Electron density \$\$\textbackslash rho (\textbackslash overrightarrow\{\{\{\{\textbackslash bf\{r\}\}\}\}\})\$\$is the fundamental variable in the calculation of ground state energy with density functional theory (DFT). Beyond total energy, features and changes in \$\$\textbackslash rho (\textbackslash overrightarrow\{\{\{\{\textbackslash bf\{r\}\}\}\}\})\$\$distributions are often used to capture critical physicochemical phenomena in functional materials. We present a machine learning framework for the prediction of \$\$\textbackslash rho (\textbackslash overrightarrow\{\{\{\{\textbackslash bf\{r\}\}\}\}\})\$\$. The model is based on equivariant graph neural networks and the electron density is predicted at special query point vertices that are part of the message-passing graph, but only receive messages. The model is tested across multiple datasets of molecules (QM9), liquid ethylene carbonate electrolyte (EC) and LixNiyMnzCo(1-y-z)O2 lithium ion battery cathodes (NMC). For QM9 molecules, the accuracy of the proposed model exceeds typical variability in \$\$\textbackslash rho (\textbackslash overrightarrow\{\{\{\{\textbackslash bf\{r\}\}\}\}\})\$\$obtained from DFT done with different exchange-correlation functionals. The accuracy on all three datasets is beyond state of the art and the computation time is orders of magnitude faster than DFT.},
+ issue = {1},
+ langid = {english},
+ keywords = {AML,DeepDFT,equivariant,GNN,liquids,materials,ML,ML-DFT,ML-ESM,molecules,MPNN,NN,prediction of electron density,QM9,VASP,with-data},
+ file = {/Users/wasmer/Nextcloud/Zotero/Jørgensen_Bhowmik_2022_Equivariant graph neural networks for fast electron density estimation of.pdf}
+}
+
@online{jorgensenGraphNeuralNetworks2021,
title = {Graph Neural Networks for Fast Electron Density Estimation of Molecules, Liquids, and Solids},
author = {Jørgensen, Peter Bjørn and Bhowmik, Arghya},
date = {2021-12-01},
- number = {arXiv:2112.00652},
- eprint = {arXiv:2112.00652},
+ eprint = {2112.00652},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.2112.00652},
url = {http://arxiv.org/abs/2112.00652},
urldate = {2022-07-10},
@@ -4196,6 +4612,22 @@
file = {/Users/wasmer/Zotero/storage/ZX3TRV7K/jukkr.fz-juelich.de.html}
}
+@online{kabaEquivariantNetworksCrystal2023,
+ title = {Equivariant {{Networks}} for {{Crystal Structures}}},
+ author = {Kaba, Sékou-Oumar and Ravanbakhsh, Siamak},
+ date = {2023-01-15},
+ eprint = {2211.15420},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2211.15420},
+ url = {http://arxiv.org/abs/2211.15420},
+ urldate = {2023-04-03},
+ abstract = {Supervised learning with deep models has tremendous potential for applications in materials science. Recently, graph neural networks have been used in this context, drawing direct inspiration from models for molecules. However, materials are typically much more structured than molecules, which is a feature that these models do not leverage. In this work, we introduce a class of models that are equivariant with respect to crystalline symmetry groups. We do this by defining a generalization of the message passing operations that can be used with more general permutation groups, or that can alternatively be seen as defining an expressive convolution operation on the crystal graph. Empirically, these models achieve competitive results with state-of-the-art on property prediction tasks.},
+ pubstate = {preprint},
+ keywords = {AML,CGCNN,crystal structure,crystal symmetry,ECN,equivariant,GNN,group theory,magnetic moment,materials,materials project,MEGNet,ML,ML-DFT,MPNN,original publication,prediction of energy,prediction of magnetic moment,supercell,voronoi tessellation},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kaba_Ravanbakhsh_2023_Equivariant Networks for Crystal Structures.pdf;/Users/wasmer/Zotero/storage/2YADPZ3J/2211.html}
+}
+
@article{kajitaDiscoverySuperionicConductors2020,
title = {Discovery of Superionic Conductors by Ensemble-Scope Descriptor},
author = {Kajita, Seiji and Ohba, Nobuko and Suzumura, Akitoshi and Tajima, Shin and Asahi, Ryoji},
@@ -4213,7 +4645,7 @@
abstract = {Machine learning accelerates virtual screening in which material candidates are selected from existing databases, facilitating materials discovery in a broad chemical search space. Machine learning models quickly predict a target property from explanatory material features called descriptors. However, a major bottleneck of the machine learning model is an insufficient amount of training data in materials science, especially data with non-equilibrium properties. Here, we develop an alternative virtual-screening process via ensemble-based machine learning with one handcrafted and two generic descriptors to maximize the inference ability even using a small training dataset. A joint representation with the three descriptors translates the physical and chemical properties of a material as well as its underlying short- and long-range atomic structures to describe a multifaceted perspective of the material. As an application, the ensemble-scope descriptor learning model was trained with only 29 entries in the training dataset, and it selected potential oxygen-ion conductors from 13,384 oxides in the inorganic crystal structure database. The experiments confirmed that we successfully discovered five compounds that have not been reported, to the best of our knowledge, as oxygen-ion conductors.},
issue = {1},
langid = {english},
- keywords = {/unread,CNN,compositional descriptors,defects,descriptor comparison,disordered,doping,KRR,model comparison,NN,prediction of ion conductivity,SOAP,supercell,VASP},
+ keywords = {bond valence sum,CNN,compositional descriptors,defects,descriptor comparison,disordered,doping,KRR,model comparison,NN,oxides,prediction from BVS,prediction of ion conductivity,SOAP,supercell,VASP},
file = {/Users/wasmer/Nextcloud/Zotero/Kajita et al_2020_Discovery of superionic conductors by ensemble-scope descriptor.pdf}
}
@@ -4268,6 +4700,26 @@
file = {/Users/wasmer/Nextcloud/Zotero/Kalita_Burke_2021_Using Machine Learning to Find New Density Functionals.pdf;/Users/wasmer/Zotero/storage/6FMA3TRD/2112.html}
}
+@article{kamalChargeDensityPrediction2020,
+ title = {A Charge Density Prediction Model for Hydrocarbons Using Deep Neural Networks},
+ author = {Kamal, Deepak and Chandrasekaran, Anand and Batra, Rohit and Ramprasad, Rampi},
+ date = {2020-03},
+ journaltitle = {Machine Learning: Science and Technology},
+ shortjournal = {Mach. Learn.: Sci. Technol.},
+ volume = {1},
+ number = {2},
+ pages = {025003},
+ publisher = {{IOP Publishing}},
+ issn = {2632-2153},
+ doi = {10.1088/2632-2153/ab5929},
+ url = {https://dx.doi.org/10.1088/2632-2153/ab5929},
+ urldate = {2023-04-13},
+ abstract = {The electronic charge density distribution Ï(r) of a given material is among the most fundamental quantities in quantum simulations from which many large scale properties and observables can be calculated. Conventionally, Ï(r) is obtained using Kohn–Sham density functional theory (KS-DFT) based methods. But, the high computational cost of KS-DFT renders it intractable for systems involving thousands/millions of atoms. Thus, recently there has been efforts to bypass expensive KS equations, and directly predict Ï(r) using machine learning (ML) based methods. Here, we build upon one such scheme to create a robust and reliable Ï(r) prediction model for a diverse set of hydrocarbons, involving huge chemical and morphological complexity /(saturated, unsaturated molecules, cyclo-groups and amorphous and semi-crystalline polymers). We utilize a grid-based fingerprint to capture the atomic neighborhood around an arbitrary point in space, and map it to the reference Ï(r) obtained from standard DFT calculations at that point. Owing to the grid-based learning, dataset sizes exceed billions of points, which is trained using deep neural networks in conjunction with a incremental learning based approach. The accuracy and transferability of the ML approach is demonstrated on not only a diverse test set, but also on a completely unseen system of polystyrene under different strains. Finally, we note that the general approach adopted here could be easily extended to other material systems, and can be used for quick and accurate determination of Ï(r) for DFT charge density initialization, computing dipole or quadrupole, and other observables for which reliable density functional are known.},
+ langid = {english},
+ keywords = {AML,grid-based descriptors,iterative learning,iterative learning scheme,ML,ML-DFT,ML-ESM,prediction of electron density,with-data},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kamal et al_2020_A charge density prediction model for hydrocarbons using deep neural networks.pdf}
+}
+
@inproceedings{kanterDeepFeatureSynthesis2015,
title = {Deep Feature Synthesis: {{Towards}} Automating Data Science Endeavors},
shorttitle = {Deep Feature Synthesis},
@@ -4342,6 +4794,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Keimer_Moore_2017_The physics of quantum materials.pdf}
}
+@article{keithCombiningMachineLearning2021,
+ title = {Combining {{Machine Learning}} and {{Computational Chemistry}} for {{Predictive Insights Into Chemical Systems}}},
+ author = {Keith, John A. and Vassilev-Galindo, Valentin and Cheng, Bingqing and Chmiela, Stefan and Gastegger, Michael and Müller, Klaus-Robert and Tkatchenko, Alexandre},
+ date = {2021-08-25},
+ journaltitle = {Chemical Reviews},
+ shortjournal = {Chem. Rev.},
+ volume = {121},
+ number = {16},
+ pages = {9816--9872},
+ publisher = {{American Chemical Society}},
+ issn = {0009-2665},
+ doi = {10.1021/acs.chemrev.1c00107},
+ url = {https://doi.org/10.1021/acs.chemrev.1c00107},
+ urldate = {2023-03-20},
+ abstract = {Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.},
+ keywords = {/unread,AML,benchmarking,chemistry,HFT,MD,ML,ML-DFT,ML-ESM,MLP,multiscale,review,review-of-AML,WFT},
+ file = {/Users/wasmer/Zotero/storage/BF3L8VHS/Keith et al. - 2021 - Combining Machine Learning and Computational Chemi.pdf;/Users/wasmer/Zotero/storage/NNJM7AKG/acs.chemrev.html}
+}
+
@article{khorshidiAmpModularApproach2016,
title = {Amp: {{A}} Modular Approach to Machine Learning in Atomistic Simulations},
shorttitle = {Amp},
@@ -4365,9 +4836,9 @@
title = {On {{Neural Differential Equations}}},
author = {Kidger, Patrick},
date = {2022-02-04},
- number = {arXiv:2202.02435},
- eprint = {arXiv:2202.02435},
+ eprint = {2202.02435},
eprinttype = {arxiv},
+ eprintclass = {cs, math, stat},
doi = {10.48550/arXiv.2202.02435},
url = {http://arxiv.org/abs/2202.02435},
urldate = {2022-09-07},
@@ -4410,7 +4881,7 @@
doi = {10.1126/science.abj6511},
url = {https://www.science.org/doi/10.1126/science.abj6511},
urldate = {2022-05-13},
- keywords = {DeepMind,density functional,DFT,DM21,ML,ML-DFA,ML-DFT,ML-ESM,molecules,original publication,with-code},
+ keywords = {DeepMind,density functional,DFT,DM21,fractional charges,fractional spin,ML,ML-DFA,ML-DFT,ML-ESM,molecules,original publication,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Kirkpatrick et al_2021_Pushing the frontiers of density functionals by solving the fractional electron.pdf}
}
@@ -4516,6 +4987,48 @@
file = {/Users/wasmer/Nextcloud/Zotero/Ko et al_2021_A fourth-generation high-dimensional neural network potential with accurate.pdf;/Users/wasmer/Zotero/storage/2Z8H4HHW/s41467-020-20427-2.html}
}
+@article{koFourthgenerationHighdimensionalNeural2021a,
+ title = {A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-Local Charge Transfer},
+ author = {Ko, Tsz Wai and Finkler, Jonas A. and Goedecker, Stefan and Behler, Jörg},
+ date = {2021-01-15},
+ journaltitle = {Nature Communications},
+ shortjournal = {Nat Commun},
+ volume = {12},
+ number = {1},
+ pages = {398},
+ publisher = {{Nature Publishing Group}},
+ issn = {2041-1723},
+ doi = {10.1038/s41467-020-20427-2},
+ url = {https://www.nature.com/articles/s41467-020-20427-2},
+ urldate = {2023-03-19},
+ abstract = {Machine learning potentials have become an important tool for atomistic simulations in many fields, from chemistry via molecular biology to materials science. Most of the established methods, however, rely on local properties and are thus unable to take global changes in the electronic structure into account, which result from long-range charge transfer or different charge states. In this work we overcome this limitation by introducing a fourth-generation high-dimensional neural network potential that combines a charge equilibration scheme employing environment-dependent atomic electronegativities with accurate atomic energies. The method, which is able to correctly describe global charge distributions in arbitrary systems, yields much improved energies and substantially extends the applicability of modern machine learning potentials. This is demonstrated for a series of systems representing typical scenarios in chemistry and materials science that are incorrectly described by current methods, while the fourth-generation neural network potential is in excellent agreement with electronic structure calculations.},
+ issue = {1},
+ langid = {english},
+ keywords = {charge transfer,FHI-aims,HDNNP,long-range interaction,materials,MD,MLP,molecules,RuNNer},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ko et al_2021_A fourth-generation high-dimensional neural network potential with accurate2.pdf}
+}
+
+@article{koFourthgenerationHighdimensionalNeural2021b,
+ title = {A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-Local Charge Transfer},
+ author = {Ko, Tsz Wai and Finkler, Jonas A. and Goedecker, Stefan and Behler, Jörg},
+ date = {2021-01-15},
+ journaltitle = {Nature Communications},
+ shortjournal = {Nat Commun},
+ volume = {12},
+ number = {1},
+ pages = {398},
+ publisher = {{Nature Publishing Group}},
+ issn = {2041-1723},
+ doi = {10.1038/s41467-020-20427-2},
+ url = {https://www.nature.com/articles/s41467-020-20427-2},
+ urldate = {2023-04-04},
+ abstract = {Machine learning potentials have become an important tool for atomistic simulations in many fields, from chemistry via molecular biology to materials science. Most of the established methods, however, rely on local properties and are thus unable to take global changes in the electronic structure into account, which result from long-range charge transfer or different charge states. In this work we overcome this limitation by introducing a fourth-generation high-dimensional neural network potential that combines a charge equilibration scheme employing environment-dependent atomic electronegativities with accurate atomic energies. The method, which is able to correctly describe global charge distributions in arbitrary systems, yields much improved energies and substantially extends the applicability of modern machine learning potentials. This is demonstrated for a series of systems representing typical scenarios in chemistry and materials science that are incorrectly described by current methods, while the fourth-generation neural network potential is in excellent agreement with electronic structure calculations.},
+ issue = {1},
+ langid = {english},
+ keywords = {AML,charge equilibration,charge transfer,electronegativity,electrostatic interaction,FHI-aims,HDNNP,long-range interaction,materials,MD,ML,MLP,molecules,NN,PBE,prediction of electronegativity},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ko et al_2021_A fourth-generation high-dimensional neural network potential with accurate3.pdf}
+}
+
@article{koGeneralPurposeMachineLearning2021,
title = {General-{{Purpose Machine Learning Potentials Capturing Nonlocal Charge Transfer}}},
author = {Ko, Tsz Wai and Finkler, Jonas A. and Goedecker, Stefan and Behler, Jörg},
@@ -4535,12 +5048,31 @@
file = {/Users/wasmer/Nextcloud/Zotero/Ko et al_2021_General-Purpose Machine Learning Potentials Capturing Nonlocal Charge Transfer.pdf}
}
-@article{kohnSelfConsistentEquationsIncluding1965,
- title = {Self-{{Consistent Equations Including Exchange}} and {{Correlation Effects}}},
- author = {Kohn, W.},
- date = {1965},
- journaltitle = {Physical Review},
- shortjournal = {Phys. Rev.},
+@article{koGeneralPurposeMachineLearning2021a,
+ title = {General-{{Purpose Machine Learning Potentials Capturing Nonlocal Charge Transfer}}},
+ author = {Ko, Tsz Wai and Finkler, Jonas A. and Goedecker, Stefan and Behler, Jörg},
+ date = {2021-02-16},
+ journaltitle = {Accounts of Chemical Research},
+ shortjournal = {Acc. Chem. Res.},
+ volume = {54},
+ number = {4},
+ pages = {808--817},
+ publisher = {{American Chemical Society}},
+ issn = {0001-4842},
+ doi = {10.1021/acs.accounts.0c00689},
+ url = {https://doi.org/10.1021/acs.accounts.0c00689},
+ urldate = {2023-03-19},
+ abstract = {ConspectusThe development of first-principles-quality machine learning potentials (MLP) has seen tremendous progress, now enabling computer simulations of complex systems for which sufficiently accurate interatomic potentials have not been available. These advances and the increasing use of MLPs for more and more diverse systems gave rise to new questions regarding their applicability and limitations, which has constantly driven new developments. The resulting MLPs can be classified into several generations depending on the types of systems they are able to describe. First-generation MLPs, as introduced 25 years ago, have been applicable to low-dimensional systems such as small molecules. MLPs became a practical tool for complex systems in chemistry and materials science with the introduction of high-dimensional neural network potentials (HDNNP) in 2007, which represented the first MLP of the second generation. Second-generation MLPs are based on the concept of locality and express the total energy as a sum of environment-dependent atomic energies, which allows applications to very large systems containing thousands of atoms with linearly scaling computational costs. Since second-generation MLPs do not consider interactions beyond the local chemical environments, a natural extension has been the inclusion of long-range interactions without truncation, mainly electrostatics, employing environment-dependent charges establishing the third MLP generation. A variety of second- and, to some extent, also third-generation MLPs are currently the standard methods in ML-based atomistic simulations.In spite of countless successful applications, in recent years it has been recognized that the accuracy of MLPs relying on local atomic energies and charges is still insufficient for systems with long-ranged dependencies in the electronic structure. These can, for instance, result from nonlocal charge transfer or ionization and are omnipresent in many important types of systems and chemical processes such as the protonation and deprotonation of organic and biomolecules, redox reactions, and defects and doping in materials. In all of these situations, small local modifications can change the system globally, resulting in different equilibrium structures, charge distributions, and reactivity. These phenomena cannot be captured by second- and third-generation MLPs. Consequently, the inclusion of nonlocal phenomena has been identified as a next key step in the development of a new fourth generation of MLPs. While a first fourth-generation MLP, the charge equilibration neural network technique (CENT), was introduced in 2015, only very recently have a range of new general-purpose methods applicable to a broad range of physical scenarios emerged. In this Account, we show how fourth-generation HDNNPs can be obtained by combining the concepts of CENT and second-generation HDNNPs. These new MLPs allow for a highly accurate description of systems where nonlocal charge transfer is important.},
+ keywords = {charge transfer,HDNNP,long-range interaction,MD,MLP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ko et al_2021_General-Purpose Machine Learning Potentials Capturing Nonlocal Charge Transfer2.pdf;/Users/wasmer/Zotero/storage/RLPWSGFJ/acs.accounts.html}
+}
+
+@article{kohnSelfConsistentEquationsIncluding1965,
+ title = {Self-{{Consistent Equations Including Exchange}} and {{Correlation Effects}}},
+ author = {Kohn, W.},
+ date = {1965},
+ journaltitle = {Physical Review},
+ shortjournal = {Phys. Rev.},
volume = {140},
pages = {A1133-A1138},
doi = {10.1103/PhysRev.140.A1133},
@@ -4583,14 +5115,50 @@
file = {/Users/wasmer/Nextcloud/Zotero/Kosma_2020_Strong spin-orbit torque effect on magnetic defects due to topological surface.pdf;/Users/wasmer/Zotero/storage/5JLDY6FT/PhysRevB.102.html}
}
+@online{kottkeScikitactivemlLibraryToolbox2021,
+ title = {Scikit-Activeml: {{A Library}} and {{Toolbox}} for {{Active Learning Algorithms}}},
+ shorttitle = {Scikit-Activeml},
+ author = {Kottke, Daniel and Herde, Marek and Minh, Tuan Pham and Benz, Alexander and Mergard, Pascal and Roghman, Atal and Sandrock, Christoph and Sick, Bernhard},
+ date = {2021-03-05},
+ number = {2021030194},
+ eprint = {2021030194},
+ eprinttype = {Preprints},
+ doi = {10.20944/preprints202103.0194.v1},
+ url = {https://www.preprints.org/manuscript/202103.0194/v1},
+ urldate = {2023-04-10},
+ abstract = {Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.},
+ langid = {english},
+ pubstate = {preprint},
+ keywords = {/unread,active learning,General ML,library,Python,scikit-learn},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kottke et al_2021_scikit-activeml.pdf}
+}
+
+@article{kouMagneticTopologicalInsulators2015,
+ title = {Magnetic Topological Insulators and Quantum Anomalous Hall Effect},
+ author = {Kou, Xufeng and Fan, Yabin and Lang, Murong and Upadhyaya, Pramey and Wang, Kang L.},
+ date = {2015-07-01},
+ journaltitle = {Solid State Communications},
+ shortjournal = {Solid State Communications},
+ volume = {215--216},
+ pages = {34--53},
+ issn = {0038-1098},
+ doi = {10.1016/j.ssc.2014.10.022},
+ url = {https://www.sciencedirect.com/science/article/pii/S0038109814004438},
+ urldate = {2023-04-06},
+ abstract = {When the magnetic order is introduced into topological insulators (TIs), the time-reversal symmetry (TRS) is broken, and the non-trivial topological surface is driven into a new massive Dirac fermions state. The study of such TRS-breaking systems is one of the most emerging frontiers in condensed-matter physics. In this review, we outline the methods to break the TRS of the topological surface states. With robust out-of-plane magnetic order formed, we describe the intrinsic magnetisms in the magnetically doped 3D TI materials and the approach to manipulate each contribution. Most importantly, we summarize the theoretical developments and experimental observations of the scale-invariant quantum anomalous Hall effect (QAHE) in both the 2D and 3D Cr-doped (BiSb)2Te3 systems; at the same time, we also discuss the correlations between QAHE and other quantum transport phenomena. Finally, we highlight the use of TI/Cr-doped TI heterostructures to both manipulate the surface-related ferromagnetism and realize electrical manipulation of magnetization through the giant spin–orbit torques.},
+ langid = {english},
+ keywords = {breaking of TRS,defects,Hall effect,Hall QAHE,heterostructures,magnetic doping,magnetic heterostructures,magnetism,physics,review,SOC,spin-dependent,Spin-orbit effects,topological insulator,TRS},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kou et al_2015_Magnetic topological insulators and quantum anomalous hall effect.pdf;/Users/wasmer/Zotero/storage/IMCZD9AZ/S0038109814004438.html}
+}
+
@online{krennPredictingFutureAI2022,
title = {Predicting the {{Future}} of {{AI}} with {{AI}}: {{High-quality}} Link Prediction in an Exponentially Growing Knowledge Network},
shorttitle = {Predicting the {{Future}} of {{AI}} with {{AI}}},
author = {Krenn, Mario and Buffoni, Lorenzo and Coutinho, Bruno and Eppel, Sagi and Foster, Jacob Gates and Gritsevskiy, Andrew and Lee, Harlin and Lu, Yichao and Moutinho, Joao P. and Sanjabi, Nima and Sonthalia, Rishi and Tran, Ngoc Mai and Valente, Francisco and Xie, Yangxinyu and Yu, Rose and Kopp, Michael},
date = {2022-09-23},
- number = {arXiv:2210.00881},
- eprint = {arXiv:2210.00881},
+ eprint = {2210.00881},
eprinttype = {arxiv},
+ eprintclass = {cs},
doi = {10.48550/arXiv.2210.00881},
url = {http://arxiv.org/abs/2210.00881},
urldate = {2022-10-05},
@@ -4621,6 +5189,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Krenn et al_2020_Self-referencing embedded strings (SELFIES).pdf}
}
+@article{kreuzbergerMachineLearningOperations2023,
+ title = {Machine {{Learning Operations}} ({{MLOps}}): {{Overview}}, {{Definition}}, and {{Architecture}}},
+ shorttitle = {Machine {{Learning Operations}} ({{MLOps}})},
+ author = {Kreuzberger, Dominik and Kühl, Niklas and Hirschl, Sebastian},
+ date = {2023},
+ journaltitle = {IEEE Access},
+ volume = {11},
+ pages = {31866--31879},
+ issn = {2169-3536},
+ doi = {10.1109/ACCESS.2023.3262138},
+ abstract = {The final goal of all industrial machine learning (ML) projects is to develop ML products and rapidly bring them into production. However, it is highly challenging to automate and operationalize ML products and thus many ML endeavors fail to deliver on their expectations. The paradigm of Machine Learning Operations (MLOps) addresses this issue. MLOps includes several aspects, such as best practices, sets of concepts, and development culture. However, MLOps is still a vague term and its consequences for researchers and professionals are ambiguous. To address this gap, we conduct mixed-method research, including a literature review, a tool review, and expert interviews. As a result of these investigations, we contribute to the body of knowledge by providing an aggregated overview of the necessary principles, components, and roles, as well as the associated architecture and workflows. Furthermore, we provide a comprehensive definition of MLOps and highlight open challenges in the field. Finally, this work provides guidance for ML researchers and practitioners who want to automate and operate their ML products with a designated set of technologies.},
+ eventtitle = {{{IEEE Access}}},
+ keywords = {Automation,CI/CD,Collaboration,DevOps,General ML,Interviews,ML,MLOps,operations,workflow orchestration},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kreuzberger et al_2023_Machine Learning Operations (MLOps).pdf;/Users/wasmer/Zotero/storage/AGAJG2J6/10081336.html}
+}
+
@article{kulikRoadmapMachineLearning2022,
title = {Roadmap on {{Machine Learning}} in {{Electronic Structure}}},
author = {Kulik, Heather and Hammerschmidt, Thomas and Schmidt, Jonathan and Botti, Silvana and Marques, Miguel A. L. and Boley, Mario and Scheffler, Matthias and Todorović, Milica and Rinke, Patrick and Oses, Corey and Smolyanyuk, Andriy and Curtarolo, Stefano and Tkatchenko, Alexandre and Bartok, Albert and Manzhos, Sergei and Ihara, Manabu and Carrington, Tucker and Behler, Jörg and Isayev, Olexandr and Veit, Max and Grisafi, Andrea and Nigam, Jigyasa and Ceriotti, Michele and Schütt, Kristoff T and Westermayr, Julia and Gastegger, Michael and Maurer, Reinhard and Kalita, Bhupalee and Burke, Kieron and Nagai, Ryo and Akashi, Ryosuke and Sugino, Osamu and Hermann, Jan and Noé, Frank and Pilati, Sebastiano and Draxl, Claudia and Kuban, Martin and Rigamonti, Santiago and Scheidgen, Markus and Esters, Marco and Hicks, David and Toher, Cormac and Balachandran, Prasanna and Tamblyn, Isaac and Whitelam, Stephen and Bellinger, Colin and Ghiringhelli, Luca M.},
@@ -4633,8 +5217,8 @@
urldate = {2022-03-28},
abstract = {In recent years, we have been witnessing a paradigm shift in computational materials science. In fact, traditional methods, mostly developed in the second half of the XXth century, are being complemented, extended, and sometimes even completely replaced by faster, simpler, and often more accurate approaches. The new approaches, that we collectively label by machine learning, have their origins in the fields of informatics and artificial intelligence, but are making rapid inroads in all other branches of science. With this in mind, this Roadmap article, consisting of multiple contributions from experts across the field, discusses the use of machine learning in materials science, and share perspectives on current and future challenges in problems as diverse as the prediction of materials properties, the construction of force-fields, the development of exchange correlation functionals for density-functional theory, the solution of the many-body problem, and more. In spite of the already numerous and exciting success stories, we are just at the beginning of a long path that will reshape materials science for the many challenges of the XXIth century.},
langid = {english},
- keywords = {_tablet,descriptors,DFT,electronic structure theory,MD,ML,ML-DFT,ML-ESM,models,review,roadmap,surrogate model},
- file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Kulik et al_2022_Roadmap on Machine Learning in Electronic Structure.pdf}
+ keywords = {descriptors,DFT,electronic structure theory,MD,ML,ML-DFT,ML-ESM,models,review,roadmap,surrogate model},
+ file = {/Users/wasmer/Nextcloud/Zotero/Kulik et al_2022_Roadmap on Machine Learning in Electronic Structure4.pdf}
}
@article{kumarTopologicalQuantumMaterials2021,
@@ -4656,14 +5240,30 @@
file = {/Users/wasmer/Nextcloud/Zotero/Kumar et al_2021_Topological Quantum Materials from the Viewpoint of Chemistry.pdf}
}
+@online{labrie-boulayMachineLearningbasedSpin2023,
+ title = {Machine Learning-Based Spin Structure Detection},
+ author = {Labrie-Boulay, Isaac and Winkler, Thomas Brian and Franzen, Daniel and Romanova, Alena and Fangohr, Hans and Kläui, Mathias},
+ date = {2023-03-24},
+ eprint = {2303.16905},
+ eprinttype = {arxiv},
+ eprintclass = {physics},
+ doi = {10.48550/arXiv.2303.16905},
+ url = {http://arxiv.org/abs/2303.16905},
+ urldate = {2023-04-12},
+ abstract = {One of the most important magnetic spin structure is the topologically stabilised skyrmion quasi-particle. Its interesting physical properties make them candidates for memory and efficient neuromorphic computation schemes. For the device operation, detection of the position, shape, and size of skyrmions is required and magnetic imaging is typically employed. A frequently used technique is magneto-optical Kerr microscopy where depending on the samples material composition, temperature, material growing procedures, etc., the measurements suffer from noise, low-contrast, intensity gradients, or other optical artifacts. Conventional image analysis packages require manual treatment, and a more automatic solution is required. We report a convolutional neural network specifically designed for segmentation problems to detect the position and shape of skyrmions in our measurements. The network is tuned using selected techniques to optimize predictions and in particular the number of detected classes is found to govern the performance. The results of this study shows that a well-trained network is a viable method of automating data pre-processing in magnetic microscopy. The approach is easily extendable to other spin structures and other magnetic imaging methods.},
+ pubstate = {preprint},
+ keywords = {CNN,computer vision,Dzyaloshinskii–Moriya interaction,experimental science,image segmentation,magnetism,ML,object detection,skyrmions,Spintronics},
+ file = {/Users/wasmer/Nextcloud/Zotero/Labrie-Boulay et al_2023_Machine learning-based spin structure detection.pdf;/Users/wasmer/Zotero/storage/SEU5QPUQ/2303.html}
+}
+
@online{lamGraphCastLearningSkillful2022,
title = {{{GraphCast}}: {{Learning}} Skillful Medium-Range Global Weather Forecasting},
shorttitle = {{{GraphCast}}},
author = {Lam, Remi and Sanchez-Gonzalez, Alvaro and Willson, Matthew and Wirnsberger, Peter and Fortunato, Meire and Pritzel, Alexander and Ravuri, Suman and Ewalds, Timo and Alet, Ferran and Eaton-Rosen, Zach and Hu, Weihua and Merose, Alexander and Hoyer, Stephan and Holland, George and Stott, Jacklynn and Vinyals, Oriol and Mohamed, Shakir and Battaglia, Peter},
date = {2022-12-24},
- number = {arXiv:2212.12794},
- eprint = {arXiv:2212.12794},
+ eprint = {2212.12794},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2212.12794},
url = {http://arxiv.org/abs/2212.12794},
urldate = {2022-12-31},
@@ -4673,6 +5273,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Lam et al_2022_GraphCast.pdf;/Users/wasmer/Zotero/storage/8UD54ESE/2212.html}
}
+@online{langerHeatFluxSemilocal2023,
+ title = {Heat Flux for Semi-Local Machine-Learning Potentials},
+ author = {Langer, Marcel F. and Knoop, Florian and Carbogno, Christian and Scheffler, Matthias and Rupp, Matthias},
+ date = {2023-03-28},
+ eprint = {2303.14434},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.2303.14434},
+ url = {http://arxiv.org/abs/2303.14434},
+ urldate = {2023-04-04},
+ abstract = {The Green-Kubo (GK) method is a rigorous framework for heat transport simulations in materials. However, it requires an accurate description of the potential-energy surface and carefully converged statistics. Machine-learning potentials can achieve the accuracy of first-principles simulations while allowing to reach well beyond their simulation time and length scales at a fraction of the cost. In this paper, we explain how to apply the GK approach to the recent class of message-passing machine-learning potentials, which iteratively consider semi-local interactions beyond the initial interaction cutoff. We derive an adapted heat flux formulation that can be implemented using automatic differentiation without compromising computational efficiency. The approach is demonstrated and validated by calculating the thermal conductivity of zirconium dioxide across temperatures.},
+ pubstate = {preprint},
+ keywords = {AML,autodiff,GKNet,GNN,Gree-Kubo,JAX,long-range interaction,materials,MD,ML,MLP,MPNN,SchNet,SchNetPack,semilocal interactions,tensorial target,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Langer et al_2023_Heat flux for semi-local machine-learning potentials.pdf;/Users/wasmer/Zotero/storage/Q6SAW6JE/2303.html}
+}
+
@unpublished{langerRepresentationsMoleculesMaterials2021,
title = {Representations of Molecules and Materials for Interpolation of Quantum-Mechanical Simulations via Machine Learning},
author = {Langer, Marcel F. and Goeßmann, Alex and Rupp, Matthias},
@@ -4683,7 +5299,7 @@
url = {http://arxiv.org/abs/2003.12081},
urldate = {2021-05-13},
abstract = {Computational study of molecules and materials from first principles is a cornerstone of physics, chemistry, and materials science, but limited by the cost of accurate and precise simulations. In settings involving many simulations, machine learning can reduce these costs, often by orders of magnitude, by interpolating between reference simulations. This requires representations that describe any molecule or material and support interpolation. We comprehensively review and discuss current representations and relations between them, using a unified mathematical framework based on many-body functions, group averaging, and tensor products. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, and Al-Ga-In sesquioxides in numerical experiments controlled for data distribution, regression method, and hyper-parameter optimization.},
- keywords = {_tablet,ACE,BoB,BS,CM,descriptors,GPR,KRR,library,materials,MBTR,ML,models,MTP,review,SOAP,with-code},
+ keywords = {_tablet,ACE,benchmarking,BoB,BS,CM,descriptors,GPR,KRR,library,materials,MBTR,ML,models,MTP,review,SOAP,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Langer et al_2021_Representations of molecules and materials for interpolation of.pdf;/Users/wasmer/Zotero/storage/5BG77UWY/2003.html}
}
@@ -4704,15 +5320,15 @@
abstract = {Computational study of molecules and materials from first principles is a cornerstone of physics, chemistry, and materials science, but limited by the cost of accurate and precise simulations. In settings involving many simulations, machine learning can reduce these costs, often by orders of magnitude, by interpolating between reference simulations. This requires representations that describe any molecule or material and support interpolation. We comprehensively review and discuss current representations and relations between them. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, and Al–Ga–In sesquioxides in numerical experiments controlled for data distribution, regression method, and hyper-parameter optimization.},
issue = {1},
langid = {english},
- keywords = {_tablet,ACE,benchmarking,BoB,BS,CM,descriptor comparison,descriptors,GPR,KRR,library,materials,MBTR,ML,models,MTP,review,SOAP,with-code},
- file = {/Users/wasmer/Nextcloud/Zotero/Langer et al_2022_Representations of molecules and materials for interpolation of.pdf;/Users/wasmer/Zotero/storage/9RVUDSSX/s41524-022-00721-x.html}
+ keywords = {_tablet,ACE,autoML,benchmarking,BoB,BS,CM,descriptor comparison,descriptors,GPR,hyperparameters optimization,KRR,library,materials,MBTR,ML,models,MTP,review,SOAP,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Langer et al_2022_Representations of molecules and materials for interpolation of.pdf;/Users/wasmer/Nextcloud/Zotero/Langer et al_2022_Representations of molecules and materials for interpolation of2.pdf;/Users/wasmer/Zotero/storage/9RVUDSSX/s41524-022-00721-x.html}
}
@article{larsenAtomicSimulationEnvironment2017,
title = {The Atomic Simulation Environment—a {{Python}} Library for Working with Atoms},
author = {Larsen, Ask Hjorth and Mortensen, Jens Jørgen and Blomqvist, Jakob and Castelli, Ivano E. and Christensen, Rune and Du\textbackslash lak, Marcin and Friis, Jesper and Groves, Michael N. and Hammer, Bjørk and Hargus, Cory and Hermes, Eric D. and Jennings, Paul C. and Jensen, Peter Bjerre and Kermode, James and Kitchin, John R. and Kolsbjerg, Esben Leonhard and Kubal, Joseph and Kaasbjerg, Kristen and Lysgaard, Steen and Maronsson, Jón Bergmann and Maxson, Tristan and Olsen, Thomas and Pastewka, Lars and Peterson, Andrew and Rostgaard, Carsten and Schiøtz, Jakob and Schütt, Ole and Strange, Mikkel and Thygesen, Kristian S. and Vegge, Tejs and Vilhelmsen, Lasse and Walter, Michael and Zeng, Zhenhua and Jacobsen, Karsten W.},
date = {2017-06},
- shortjournal = {J. Phys.: Condens. Matter},
+ journaltitle = {J. Phys.: Condens. Matter},
volume = {29},
number = {27},
pages = {273002},
@@ -4838,7 +5454,7 @@
url = {http://arxiv.org/abs/2106.05364},
urldate = {2021-06-29},
abstract = {We introduce a local machine-learning method for predicting the electron densities of periodic systems. The framework is based on a numerical, atom-centred auxiliary basis, which enables an accurate expansion of the all-electron density in a form suitable for learning isolated and periodic systems alike. We show that using this formulation the electron densities of metals, semiconductors and molecular crystals can all be accurately predicted using a symmetry-adapted Gaussian process regression model, properly adjusted for the non-orthogonal nature of the basis. These predicted densities enable the efficient calculation of electronic properties which present errors on the order of tens of meV/atom when compared to ab initio density-functional calculations. We demonstrate the key power of this approach by using a model trained on ice unit cells containing only 4 water molecules to predict the electron densities of cells containing up to 512 molecules, and see no increase in the magnitude of the errors of derived electronic properties when increasing the system size. Indeed, we find that these extrapolated derived energies are more accurate than those predicted using a direct machine-learning model.},
- keywords = {DFT,GPR,library,ML,ML-DFT,ML-ESM,models,molecules,molecules & solids,prediction of electron density,prediction of ground-state properties,Resolution of the identity,SA-GPR,SALTED,solids,with-code},
+ keywords = {DFT,GPR,lambda-SOAP,library,ML,ML-DFT,ML-ESM,models,molecules,molecules & solids,prediction of electron density,prediction of ground-state properties,Resolution of the identity,SA-GPR,SALTED,solids,with-code},
file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Lewis et al_2021_Learning electron densities in the condensed-phase.pdf;/Users/wasmer/Zotero/storage/IC2NJGYT/2106.html}
}
@@ -4857,10 +5473,31 @@
url = {https://doi.org/10.1021/acs.jctc.1c00576},
urldate = {2022-08-22},
abstract = {We introduce a local machine-learning method for predicting the electron densities of periodic systems. The framework is based on a numerical, atom-centered auxiliary basis, which enables an accurate expansion of the all-electron density in a form suitable for learning isolated and periodic systems alike. We show that, using this formulation, the electron densities of metals, semiconductors, and molecular crystals can all be accurately predicted using symmetry-adapted Gaussian process regression models, properly adjusted for the nonorthogonal nature of the basis. These predicted densities enable the efficient calculation of electronic properties, which present errors on the order of tens of meV/atom when compared to ab initio density-functional calculations. We demonstrate the key power of this approach by using a model trained on ice unit cells containing only 4 water molecules to predict the electron densities of cells containing up to 512 molecules and see no increase in the magnitude of the errors of derived electronic properties when increasing the system size. Indeed, we find that these extrapolated derived energies are more accurate than those predicted using a direct machine-learning model. Finally, on heterogeneous data sets SALTED can predict electron densities with errors below 4\%.},
- keywords = {_tablet,DFT,GPR,library,ML,ML-DFT,ML-ESM,models,molecules,molecules & solids,prediction of electron density,prediction of ground-state properties,Resolution of the identity,SA-GPR,SALTED,solids,with-code},
+ keywords = {_tablet,DFT,GPR,lambda-SOAP,library,ML,ML-DFT,ML-ESM,models,molecules,molecules & solids,prediction of electron density,prediction of ground-state properties,Resolution of the identity,SA-GPR,SALTED,solids,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Lewis et al_2021_Learning Electron Densities in the Condensed Phase.pdf;/Users/wasmer/Zotero/storage/S9FT2FEZ/acs.jctc.html}
}
+@article{liDeeplearningDensityFunctional2022,
+ title = {Deep-Learning Density Functional Theory {{Hamiltonian}} for Efficient Ab Initio Electronic-Structure Calculation},
+ author = {Li, He and Wang, Zun and Zou, Nianlong and Ye, Meng and Xu, Runzhang and Gong, Xiaoxun and Duan, Wenhui and Xu, Yong},
+ date = {2022-06},
+ journaltitle = {Nature Computational Science},
+ shortjournal = {Nat Comput Sci},
+ volume = {2},
+ number = {6},
+ pages = {367--377},
+ publisher = {{Nature Publishing Group}},
+ issn = {2662-8457},
+ doi = {10.1038/s43588-022-00265-6},
+ url = {https://www.nature.com/articles/s43588-022-00265-6},
+ urldate = {2023-04-13},
+ abstract = {The marriage of density functional theory (DFT) and deep-learning methods has the potential to revolutionize modern computational materials science. Here we develop a deep neural network approach to represent the DFT Hamiltonian (DeepH) of crystalline materials, aiming to bypass the computationally demanding self-consistent field iterations of DFT and substantially improve the efficiency of ab initio electronic-structure calculations. A general framework is proposed to deal with the large dimensionality and gauge (or rotation) covariance of the DFT Hamiltonian matrix by virtue of locality, and this is realized by a message-passing neural network for deep learning. High accuracy, high efficiency and good transferability of the DeepH method are generally demonstrated for various kinds of material system and physical property. The method provides a solution to the accuracy–efficiency dilemma of DFT and opens opportunities to explore large-scale material systems, as evidenced by a promising application in the study of twisted van der Waals materials.},
+ issue = {6},
+ langid = {english},
+ keywords = {/unread,Computational methods,Electronic properties and materials,Electronic structure},
+ file = {/Users/wasmer/Nextcloud/Zotero/Li et al_2022_Deep-learning density functional theory Hamiltonian for efficient ab initio.pdf}
+}
+
@unpublished{liDeepNeuralNetwork2021,
title = {Deep {{Neural Network Representation}} of {{Density Functional Theory Hamiltonian}}},
author = {Li, He and Wang, Zun and Zou, Nianlong and Ye, Meng and Duan, Wenhui and Xu, Yong},
@@ -4950,9 +5587,9 @@
title = {Troubling {{Trends}} in {{Machine Learning Scholarship}}},
author = {Lipton, Zachary C. and Steinhardt, Jacob},
date = {2018-07-26},
- number = {arXiv:1807.03341},
- eprint = {arXiv:1807.03341},
+ eprint = {1807.03341},
eprinttype = {arxiv},
+ eprintclass = {cs, stat},
doi = {10.48550/arXiv.1807.03341},
url = {http://arxiv.org/abs/1807.03341},
urldate = {2022-06-27},
@@ -4997,6 +5634,20 @@
file = {/Users/wasmer/Nextcloud/Zotero/Liu et al_2017_Improving the Performance of Long-Range-Corrected Exchange-Correlation.pdf;/Users/wasmer/Zotero/storage/76EWRKPT/acs.jpca.html}
}
+@article{liuLargeScaleDataset2022,
+ title = {Large Scale Dataset of Real Space Electronic Charge Density of Cubic Inorganic Materials from Density Functional Theory ({{DFT}}) Calculations},
+ author = {Liu, Yu},
+ date = {2022-02-14T11:52:45+00:00},
+ publisher = {{figshare}},
+ doi = {10.6084/m9.figshare.c.5368343.v1},
+ url = {https://springernature.figshare.com/collections/Large_scale_dataset_of_real_space_electronic_charge_density_of_cubic_inorganic_materials_from_density_functional_theory_DFT_calculations/5368343},
+ urldate = {2023-04-14},
+ abstract = {the material IDs along with the energy above hull of each structure},
+ langid = {english},
+ keywords = {/unread,binary systems,Carolina Materials Database,Database,database of electron density,Heusler,inorganic materials,materials,materials project,prediction of electron density,quaternary systems,ternary systems,VASP},
+ file = {/Users/wasmer/Zotero/storage/JX4G37PC/5368343.html}
+}
+
@article{liuMagneticTopologicalInsulator,
title = {Magnetic {{Topological Insulator Heterostructures}}: {{A Review}}},
shorttitle = {Magnetic {{Topological Insulator Heterostructures}}},
@@ -5011,7 +5662,7 @@
urldate = {2023-03-15},
abstract = {Topological insulators (TIs) provide intriguing prospects for the future of spintronics due to their large spin–orbit coupling and dissipationless, counter-propagating conduction channels in the surface state. The combination of topological properties and magnetic order can lead to new quantum states including the quantum anomalous Hall effect that was first experimentally realized in Cr-doped (Bi,Sb)2Te3 films. Since magnetic doping can introduce detrimental effects, requiring very low operational temperatures, alternative approaches are explored. Proximity coupling to magnetically ordered systems is an obvious option, with the prospect to raise the temperature for observing the various quantum effects. Here, an overview of proximity coupling and interfacial effects in TI heterostructures is presented, which provides a versatile materials platform for tuning the magnetic and topological properties of these exciting materials. An introduction is first given to the heterostructure growth by molecular beam epitaxy and suitable structural, electronic, and magnetic characterization techniques. Going beyond transition-metal-doped and undoped TI heterostructures, examples of heterostructures are discussed, including rare-earth-doped TIs, magnetic insulators, and antiferromagnets, which lead to exotic phenomena such as skyrmions and exchange bias. Finally, an outlook on novel heterostructures such as intrinsic magnetic TIs and systems including 2D materials is given.},
langid = {english},
- keywords = {/unread,heterostructures,impurity embedding,magnetic heterostructures,magnetism,physics,proximity effect,review,topological insulator},
+ keywords = {heterostructures,impurity embedding,magnetic heterostructures,magnetism,physics,proximity effect,review,topological insulator},
file = {/Users/wasmer/Nextcloud/Zotero/Liu_Hesjedal_Magnetic Topological Insulator Heterostructures.pdf;/Users/wasmer/Zotero/storage/77XG2Q59/adma.html}
}
@@ -5108,9 +5759,9 @@
title = {Modeling High-Entropy Transition-Metal Alloys with Alchemical Compression},
author = {Lopanitsyna, Nataliya and Fraux, Guillaume and Springer, Maximilian A. and De, Sandip and Ceriotti, Michele},
date = {2022-12-26},
- number = {arXiv:2212.13254},
- eprint = {arXiv:2212.13254},
+ eprint = {2212.13254},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2212.13254},
url = {http://arxiv.org/abs/2212.13254},
urldate = {2022-12-29},
@@ -5162,9 +5813,9 @@
shorttitle = {Surfing Multiple Conformation-Property Landscapes via Machine Learning},
author = {Lunghi, Alessandro and Sanvito, Stefano},
date = {2019-11-06},
- number = {arXiv:1911.02263},
- eprint = {arXiv:1911.02263},
+ eprint = {1911.02263},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.1911.02263},
url = {http://arxiv.org/abs/1911.02263},
urldate = {2023-02-23},
@@ -5178,15 +5829,15 @@
title = {Active Learning Strategies for Atomic Cluster Expansion Models},
author = {Lysogorskiy, Yury and Bochkarev, Anton and Mrovec, Matous and Drautz, Ralf},
date = {2022-12-16},
- number = {arXiv:2212.08716},
- eprint = {arXiv:2212.08716},
+ eprint = {2212.08716},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2212.08716},
url = {http://arxiv.org/abs/2212.08716},
urldate = {2023-01-20},
abstract = {The atomic cluster expansion (ACE) was proposed recently as a new class of data-driven interatomic potentials with a formally complete basis set. Since the development of any interatomic potential requires a careful selection of training data and thorough validation, an automation of the construction of the training dataset as well as an indication of a model's uncertainty are highly desirable. In this work, we compare the performance of two approaches for uncertainty indication of ACE models based on the D-optimality criterion and ensemble learning. While both approaches show comparable predictions, the extrapolation grade based on the D-optimality (MaxVol algorithm) is more computationally efficient. In addition, the extrapolation grade indicator enables an active exploration of new structures, opening the way to the automated discovery of rare-event configurations. We demonstrate that active learning is also applicable to explore local atomic environments from large-scale MD simulations.},
pubstate = {preprint},
- keywords = {ACE,active learning,Condensed Matter - Materials Science,D-optimality,descriptors,ensemble learning,MD,molecular dynamics,uncertainty quantification},
+ keywords = {ACE,active learning,Condensed Matter - Materials Science,D-optimality,database generation],descriptors,ensemble learning,iterative learning,iterative learning scheme,MD,molecular dynamics,uncertainty quantification},
file = {/Users/wasmer/Nextcloud/Zotero/Lysogorskiy et al_2022_Active learning strategies for atomic cluster expansion models.pdf;/Users/wasmer/Zotero/storage/67ZIBP4V/2212.html}
}
@@ -5263,7 +5914,7 @@
url = {https://www.frontiersin.org/articles/10.3389/fmats.2021.673574},
urldate = {2023-03-15},
abstract = {Multi-principal element alloys (MPEAs) are a new class of alloys that consist of many principal elements randomly distributed on a crystal lattice. The random presence of many elements lends large variations in the point defect formation and migration energies even within a given alloy composition. Compounded by the fact that there could be exponentially large number of MPEA compositions, there is a major computational challenge to capture complete point-defect energy phase-space in MPEAs. In this work, we present a machine learning based framework in which the point defect energies in MPEAs are predicted from a database of their constituent binary alloys. We demonstrate predictions of vacancy migration and formation energies in face centered cubic ternary, quaternary and quinary alloys in Ni-Fe-Cr-Co-Cu system. A key benefit of building this framework based on the database of binary alloys is that it enables defect-energy predictions in alloy compositions that may be unearthed in future. Furthermore, the methodology enables identifying the impact of a given alloying element on the defect energies thereby enabling design of alloys with tailored defect properties.},
- keywords = {AML,defects,descriptors,disordered,impurity embedding,LAMMPS,MD,ML,multi-principal element alloys,NEB,point defects,prediction from structure,prediction of energy,prediction of vacancy migration energy,supercell,TODO,vacancies},
+ keywords = {/unread,AML,defects,descriptors,disordered,impurity embedding,LAMMPS,MD,ML,multi-principal element alloys,NEB,point defects,prediction from structure,prediction of energy,prediction of vacancy migration energy,supercell,TODO,vacancies},
file = {/Users/wasmer/Nextcloud/Zotero/Manzoor et al_2021_Machine Learning Based Methodology to Predict Point Defect Energies in.pdf}
}
@@ -5284,10 +5935,28 @@
abstract = {Density-functional theory (DFT) is a rigorous and (in principle) exact framework for the description of the ground state properties of atoms, molecules and solids based on their electron density. While computationally efficient density-functional approximations (DFAs) have become essential tools in computational chemistry, their (semi-)local treatment of electron correlation has a number of well-known pathologies, e.g. related to electron self-interaction. Here, we present a type of machine-learning (ML) based DFA (termed Kernel Density Functional Approximation, KDFA) that is pure, non-local and transferable, and can be efficiently trained with fully quantitative reference methods. The functionals retain the mean-field computational cost of common DFAs and are shown to be applicable to non-covalent, ionic and covalent interactions, as well as across different system sizes. We demonstrate their remarkable possibilities by computing the free energy surface for the protonated water dimer at hitherto unfeasible gold-standard coupled cluster quality on a single commodity workstation.},
issue = {1},
langid = {english},
+ keywords = {AML,KDFA,library,long-range interaction,ML,ML-DFA,ML-DFT,ML-ESM,prediction of Exc},
annotation = {Bandiera\_abtest: a Cc\_license\_type: cc\_by Cg\_type: Nature Research Journals Primary\_atype: Research Subject\_term: Computational chemistry;Density functional theory;Method development;Molecular dynamics Subject\_term\_id: computational-chemistry;density-functional-theory;method-development;molecular-dynamics},
file = {/Users/wasmer/Nextcloud/Zotero/Margraf_Reuter_2021_Pure non-local machine-learned density functional theory for electron.pdf;/Users/wasmer/Zotero/storage/RCFG2NBC/s41467-020-20471-y.html}
}
+@article{margrafScienceDrivenAtomisticMachine2023,
+ title = {Science-{{Driven Atomistic Machine Learning}}},
+ author = {Margraf, Johannes},
+ date = {2023-03-10},
+ journaltitle = {Angewandte Chemie},
+ volume = {n/a},
+ number = {n/a},
+ issn = {1521-3757},
+ doi = {10.1002/ange.202219170},
+ url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/ange.202219170},
+ urldate = {2023-03-20},
+ abstract = {Machine learning (ML) algorithms are currently emerging as powerful tools in all areas of science. Conventionally, ML is understood as a fundamentally data-driven endeavour. Unfortunately, large well-curated databases are sparse in chemistry. In this contribution, I therefore review science-driven ML approaches which do not rely on “big dataâ€, focusing on the atomistic modelling of materials and molecules. In this context, the term science-driven refers to approaches that begin with a scientific question and then ask what training data and model design choices are appropriate. As key features of science-driven ML, the automated and purpose-driven collection of data and the use of chemical and physical priors to achieve high data-efficiency are discussed. Furthermore, the importance of appropriate model evaluation and error estimation is emphasized.},
+ langid = {english},
+ keywords = {_tablet,active learning,all-electron,AML,body-order,data-driven,database generation,delta learning,equivariant,inductive bias,iterative learning,iterative learning scheme,MACE,ML,ML-DFA,ML-DFT,ML-ESM,model evaluation,physical prior,physics-informed ML,prediction of electron density,review,review-of-AML,science-driven,uncertainty quantification},
+ file = {/Users/wasmer/Zotero/storage/LIPPS6I7/Margraf_2023_Science-Driven Atomistic Machine Learning.pdf;/Users/wasmer/Zotero/storage/V3VTFITJ/ange.html}
+}
+
@online{MARVELDistinguishedLecture,
title = {{{MARVEL Distinguished Lecture}} — {{Georg Kresse}} - {{Events}} - Nccr-Marvel.Ch :: {{NCCR MARVEL}}},
url = {https://nccr-marvel.ch/events/marvel-distinguished-lecture-GeorgKresse},
@@ -5431,6 +6100,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Merker et al_2022_Machine learning magnetism classifiers from atomic coordinates.pdf;/Users/wasmer/Zotero/storage/7UQX89UL/S258900422201464X.html}
}
+@article{merkerMachineLearningMagnetism2022a,
+ title = {Machine Learning Magnetism Classifiers from Atomic Coordinates},
+ author = {Merker, Helena A. and Heiberger, Harry and Nguyen, Linh and Liu, Tongtong and Chen, Zhantao and Andrejevic, Nina and Drucker, Nathan C. and Okabe, Ryotaro and Kim, Song Eun and Wang, Yao and Smidt, Tess and Li, Mingda},
+ date = {2022-10-21},
+ journaltitle = {iScience},
+ shortjournal = {iScience},
+ volume = {25},
+ number = {10},
+ pages = {105192},
+ issn = {2589-0042},
+ doi = {10.1016/j.isci.2022.105192},
+ url = {https://www.sciencedirect.com/science/article/pii/S258900422201464X},
+ urldate = {2023-04-03},
+ abstract = {The determination of magnetic structure poses a long-standing challenge in condensed matter physics and materials science. Experimental techniques such as neutron diffraction are resource-limited and require complex structure refinement protocols, while computational approaches such as first-principles density functional theory (DFT) need additional semi-empirical correction, and reliable prediction is still largely limited to collinear magnetism. Here, we present a machine learning model that aims to classify the magnetic structure by inputting atomic coordinates containing transition metal and rare earth elements. By building a Euclidean equivariant neural network that preserves the crystallographic symmetry, the magnetic structure (ferromagnetic, antiferromagnetic, and non-magnetic) and magnetic propagation vector (zero or non-zero) can be predicted with an average accuracy of 77.8\% and 73.6\%. In particular, a 91\% accuracy is reached when predicting no magnetic ordering even if the structure contains magnetic element(s). Our work represents one step forward to solving the grand challenge of full magnetic structure determination.},
+ langid = {english},
+ keywords = {AFM,AML,classification,classification of magnetic structure,collinear,e3nn,electronegativity,equivariant,FM,GNN,MAGNDATA,magnetic order,magnetic structure,magnetism,magnetism database,materials,materials project,ML,MPNN,non-collinear,polarizability,prediction of magnetic order,propagation vector,rare earths,spin-dependent,transition metals,vectorial learning target,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Merker et al_2022_Machine learning magnetism classifiers from atomic coordinates2.pdf;/Users/wasmer/Zotero/storage/7YNIAY2A/S258900422201464X.html}
+}
+
@article{merkysPosterioriMetadataAutomated2017,
title = {A Posteriori Metadata from Automated Provenance Tracking: Integration of {{AiiDA}} and {{TCOD}}},
shorttitle = {A Posteriori Metadata from Automated Provenance Tracking},
@@ -5450,6 +6138,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Merkys et al_2017_A posteriori metadata from automated provenance tracking.pdf;/Users/wasmer/Zotero/storage/9ZIMVPJ8/s13321-017-0242-y.html}
}
+@online{minotakisMachineLearningSurrogateModel2023,
+ title = {Machine-{{Learning Surrogate Model}} for {{Accelerating}} the {{Search}} of {{Stable Ternary Alloys}}},
+ author = {Minotakis, Michael and Rossignol, Hugo and Cobelli, Matteo and Sanvito, Stefano},
+ date = {2023-03-29},
+ eprint = {2303.16597},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2303.16597},
+ url = {http://arxiv.org/abs/2303.16597},
+ urldate = {2023-04-13},
+ abstract = {The prediction of phase diagrams in the search for new phases is a complex and computationally intensive task. Density functional theory provides, in many situations, the desired accuracy, but its throughput becomes prohibitively limited as the number of species involved grows, even when used with local and semi-local functionals. Here, we explore the possibility of integrating machine-learning models in the workflow for the construction of ternary convex hull diagrams. In particular, we train a set of spectral neighbour-analysis potentials (SNAPs) over readily available binary phases and we establish whether this is good enough to predict the energies of novel ternaries. Such a strategy does not require any new calculations specific for the construction of the model, but just avails of data stored in binary-phase-diagram repositories. We find that a so-constructed SNAP is capable of accurate total-energy estimates for ternary phases close to the equilibrium geometry but, in general, is not able to perform atomic relaxation. This is because during a typical relaxation path a given phase traverses regions in the parameter space poorly represented by the training set. Different metrics are then investigated to assess how an unknown structure is well described by a given SNAP model, and we find that the standard deviation of an ensemble of SNAPs provides a fast and non-specie-specific metric.},
+ pubstate = {preprint},
+ keywords = {AFLOW,AFLOWLIB,AML,binary systems,convex hull,High-throughput,LAMMPS,materials discovery,materials screening,ML,MLP,MTP,PCA,phase diagram,prediction of energy,scikit-learn,SNAP,structure relaxation,ternary systems,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Minotakis et al_2023_Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary.pdf;/Users/wasmer/Zotero/storage/L8VGVV3E/2303.html}
+}
+
@inproceedings{missierW3CPROVFamily2013,
title = {The {{W3C PROV}} Family of Specifications for Modelling Provenance Metadata},
booktitle = {Proceedings of the 16th {{International Conference}} on {{Extending Database Technology}}},
@@ -5467,6 +6171,42 @@
file = {/Users/wasmer/Nextcloud/Zotero/Missier et al_2013_The W3C PROV family of specifications for modelling provenance metadata.pdf}
}
+@article{mitranGroundStateCharge2021,
+ title = {Ground State Charge Density Prediction in {{C-BN}} Nanoflakes Using Rotation Equivariant Feature-Free Artificial Neural Networks},
+ author = {Mitran, Tudor Luca and Nemnes, George Alexandru},
+ date = {2021-04-15},
+ journaltitle = {Carbon},
+ shortjournal = {Carbon},
+ volume = {174},
+ pages = {276--283},
+ issn = {0008-6223},
+ doi = {10.1016/j.carbon.2020.12.048},
+ url = {https://www.sciencedirect.com/science/article/pii/S0008622320312252},
+ urldate = {2023-04-14},
+ abstract = {Ab initio methods have been the workhorse for the computational investigation of new materials during the past few decades. In spite of the improvements regarding the efficiency and scalability achieved by various implementations, the self-consistent solution of the Konhn-Sham equations remains challenging as the size of the system increases. We propose here machine learning methods based on a feature-free deep ANN approach that are able to predict the ground state charge density by starting from readily accessible free-atom charge densities, thus bypassing the usual Hamiltonian diagonalization. We validate our approach on hybrid C-BN nanoflakes with random atomic configurations by comparing the predicted charge density to that computed by DFT. The ANN architecture is optimized in order to reach the high prediction accuracy required to extract ground state based material properties. In order to correlate the effect of spatial rotations in the input-output mapping, we introduce a novel rotational equivariant network (RE-ANN), by properly symmetrizing the synaptic weights during training. This regularization procedure enhances the prediction accuracy, provides consistent results under rotation operations and also increases the sparsity of the weight matrix. These methods have the potential to speed-up DFT simulations and can be used as high throughput investigation tools.},
+ langid = {english},
+ keywords = {AML,equivariant,ML,ML-DFT,ML-ESM,NN,prediction of electron density},
+ file = {/Users/wasmer/Zotero/storage/X264Q7JM/S0008622320312252.html}
+}
+
+@article{moldabekovNonempiricalMixingCoefficient2023,
+ title = {Non-Empirical {{Mixing Coefficient}} for {{Hybrid XC Functionals}} from {{Analysis}} of the {{XC Kernel}}},
+ author = {Moldabekov, Zhandos A. and Lokamani, Mani and Vorberger, Jan and Cangi, Attila and Dornheim, Tobias},
+ date = {2023-02-09},
+ journaltitle = {The Journal of Physical Chemistry Letters},
+ shortjournal = {J. Phys. Chem. Lett.},
+ volume = {14},
+ number = {5},
+ pages = {1326--1333},
+ publisher = {{American Chemical Society}},
+ doi = {10.1021/acs.jpclett.2c03670},
+ url = {https://doi.org/10.1021/acs.jpclett.2c03670},
+ urldate = {2023-04-04},
+ abstract = {We present an analysis of the static exchange-correlation (XC) kernel computed from hybrid functionals with a single mixing coefficient such as PBE0 and PBE0–1/3. We break down the hybrid XC kernels into the exchange and correlation parts using the Hartree–Fock functional, the exchange-only PBE, and the correlation-only PBE. This decomposition is combined with exact data for the static XC kernel of the uniform electron gas and an Airy gas model within a subsystem functional approach. This gives us a tool for the non-empirical choice of the mixing coefficient under ambient and extreme conditions. Our analysis provides physical insights into the effect of the variation of the mixing coefficient in hybrid functionals, which is of immense practical value. The presented approach is general and can be used for other types of functionals like screened hybrids.},
+ keywords = {/unread,CASUS,DFA,DFT,HZDR,PGI-1/IAS-1},
+ file = {/Users/wasmer/Nextcloud/Zotero/Moldabekov et al_2023_Non-empirical Mixing Coefficient for Hybrid XC Functionals from Analysis of the.pdf;/Users/wasmer/Zotero/storage/WGXJ5PMF/acs.jpclett.html}
+}
+
@book{molnarGlobalSurrogateInterpretable,
title = {5.6 {{Global Surrogate}} | {{Interpretable Machine Learning}}},
author = {Molnar, Christoph},
@@ -5567,9 +6307,9 @@
title = {How to Validate Machine-Learned Interatomic Potentials},
author = {Morrow, Joe D. and Gardner, John L. A. and Deringer, Volker L.},
date = {2022-11-28},
- number = {arXiv:2211.12484},
- eprint = {arXiv:2211.12484},
+ eprint = {2211.12484},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2211.12484},
url = {http://arxiv.org/abs/2211.12484},
urldate = {2023-01-02},
@@ -5582,7 +6322,7 @@
@thesis{mozumderDesignMagneticInteractions2022,
type = {mathesis},
title = {Design of Magnetic Interactions in Doped Topological Insulators},
- author = {Mozumder, Rubel},
+ author = {Mozumder, Rubel and Rüßmann, Philipp and Blügel, Stefan},
date = {2022-04-12},
institution = {{Heinrich Heine University Düsseldorf}},
abstract = {Magnetic impurities and their long-range interaction (ferromagnetic) order play pivotal roles in the topological phase transition from QSHI to QAHI. This transition transforms helical edge states belonging to the QSHI for 2D TIs (surface states for 3D TI) to the chiral edge states in QAHI for 2D TIs (surface states for 3D TI). Due to such chiral states, the QAHIs forbid back-scattering in electron conducting channels, which in turn provide passionless current and increase energy efficiency for conduct- ing channels. The chiral states are consist of single spin electrons which provide spin currents from conventional charge currents. Regarding the properties of QAHIs, the QAHIs opens a new venue for low-energy elec- tronics, spintronics and quantum computation [9]. Independently, the V- [10] and Cr-doped [11] as well as their co-doping [12] (Sb, Bi)2 Te3 shows stable QAHE but with very low temperatures (≤ 0.5K). In this high throughput ab-initio work, we will investigate other possible co-doping, dimer calculations, from the d-block elements in 3D TI Bi2 Te3 . For this purpose, we have extended AiiDA-KKR plugins by developing combine- impurity workflow called combine imps wc using GF formulation of DFT code (KKR-GF method) and the new workflow is capable to run multi- impurity calculations. Here, the dimer calculations are in the main fo- cus, and from the calculation results we will analyze Heisenberg isotropic collinear interaction (Jij ), Dzyaloshinskii–Moriya interaction (DMI, Dij ), and their ratio for each possible impurity couple. Finally, using the ob- tained Jij data we have implemented some linear regression machine learn- ing tools to understand better the dependency of Jij on some well-known factors e.g. inter-impurity distance, electronegativity. Our results from the notion of this work will give a list of some potential impurities and after their potential impurity combinations for stable QAHE. It will also render an impression of implementation of machine learning approach for designing better magnetic interactions in TIs.},
@@ -5630,6 +6370,27 @@
file = {/Users/wasmer/Nextcloud/Zotero/Musaelian et al_2022_Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics.pdf;/Users/wasmer/Zotero/storage/3GTGKKHF/2204.html}
}
+@article{musaelianLearningLocalEquivariant2023,
+ title = {Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics},
+ author = {Musaelian, Albert and Batzner, Simon and Johansson, Anders and Sun, Lixin and Owen, Cameron J. and Kornbluth, Mordechai and Kozinsky, Boris},
+ date = {2023-02-03},
+ journaltitle = {Nature Communications},
+ shortjournal = {Nat Commun},
+ volume = {14},
+ number = {1},
+ pages = {579},
+ publisher = {{Nature Publishing Group}},
+ issn = {2041-1723},
+ doi = {10.1038/s41467-023-36329-y},
+ url = {https://www.nature.com/articles/s41467-023-36329-y},
+ urldate = {2023-03-20},
+ abstract = {A simultaneously accurate and computationally efficient parametrization of the potential energy surface of molecules and materials is a long-standing goal in the natural sciences. While atom-centered message passing neural networks (MPNNs) have shown remarkable accuracy, their information propagation has limited the accessible length-scales. Local methods, conversely, scale to large simulations but have suffered from inferior accuracy. This work introduces Allegro, a strictly local equivariant deep neural network interatomic potential architecture that simultaneously exhibits excellent accuracy and scalability. Allegro represents a many-body potential using iterated tensor products of learned equivariant representations without atom-centered message passing. Allegro obtains improvements over state-of-the-art methods on QM9 and revMD17. A single tensor product layer outperforms existing deep MPNNs and transformers on QM9. Furthermore, Allegro displays remarkable generalization to out-of-distribution data. Molecular simulations using Allegro recover structural and kinetic properties of an amorphous electrolyte in excellent agreement with ab-initio simulations. Finally, we demonstrate parallelization with a simulation of 100 million atoms.},
+ issue = {1},
+ langid = {english},
+ keywords = {/unread,Allegro,AML,chemical species scaling problem,equivariant,local,MD,MD17,ML,MLP,MPNN,NequIP,original publication,parallelization,prediction of total energy,QM9,scaling,SE(3)},
+ file = {/Users/wasmer/Zotero/storage/INEV8259/Musaelian et al. - 2023 - Learning local equivariant representations for lar.pdf}
+}
+
@article{musilEfficientImplementationAtomdensity2021,
title = {Efficient Implementation of Atom-Density Representations},
author = {Musil, Félix and Veit, Max and Goscinski, Alexander and Fraux, Guillaume and Willatt, Michael J. and Stricker, Markus and Junge, Till and Ceriotti, Michele},
@@ -5662,10 +6423,10 @@
issn = {1549-9618},
doi = {10.1021/acs.jctc.8b00959},
url = {https://doi.org/10.1021/acs.jctc.8b00959},
- urldate = {2021-05-30},
+ urldate = {2023-04-11},
abstract = {We present a scheme to obtain an inexpensive and reliable estimate of the uncertainty associated with the predictions of a machine-learning model of atomic and molecular properties. The scheme is based on resampling, with multiple models being generated based on subsampling of the same training data. The accuracy of the uncertainty prediction can be benchmarked by maximum likelihood estimation, which can also be used to correct for correlations between resampled models and to improve the performance of the uncertainty estimation by a cross-validation procedure. In the case of sparse Gaussian Process Regression models, this resampled estimator can be evaluated at negligible cost. We demonstrate the reliability of these estimates for the prediction of molecular and materials energetics and for the estimation of nuclear chemical shieldings in molecular crystals. Extension to estimate the uncertainty in energy differences, forces, or other correlated predictions is straightforward. This method can be easily applied to other machine-learning schemes and will be beneficial to make data-driven predictions more reliable and to facilitate training-set optimization and active-learning strategies.},
- keywords = {descriptors,GPR,library,ML,models,SA-GPR,SOAP,uncertainty quantification,with-code},
- file = {/Users/wasmer/Nextcloud/Zotero/Musil et al_2019_Fast and Accurate Uncertainty Estimation in Chemical Machine Learning.pdf;/Users/wasmer/Zotero/storage/PGUZKGX5/acs.jctc.html}
+ keywords = {active learning,Bayesian methods,descriptors,Gaussian process,GPR,iterative learning,library,maximum likelihood,ML,MLE,models,QM9,SA-GPR,sampling,SOAP,uncertainty quantification,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Musil et al_2019_Fast and Accurate Uncertainty Estimation in Chemical Machine Learning2.pdf;/Users/wasmer/Zotero/storage/8S7ZQ3FF/acs.jctc.html}
}
@article{musilMachineLearningAtomic2019,
@@ -5888,9 +6649,9 @@
title = {Completeness of {{Atomic Structure Representations}}},
author = {Nigam, Jigyasa and Pozdnyakov, Sergey N. and Huguenin-Dumittan, Kevin K. and Ceriotti, Michele},
date = {2023-02-28},
- number = {arXiv:2302.14770},
- eprint = {arXiv:2302.14770},
+ eprint = {2302.14770},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2302.14770},
url = {http://arxiv.org/abs/2302.14770},
urldate = {2023-03-01},
@@ -5933,6 +6694,25 @@
file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Nigam et al_2022_Unified theory of atom-centered representations and graph convolutional.pdf}
}
+@article{ningFullpotentialKKRRemovedsphere2022,
+ title = {Full-Potential {{KKR}} within the Removed-Sphere Method: {{A}} Practical and Accurate Solution to the {{Poisson}} Equation},
+ shorttitle = {Full-Potential {{KKR}} within the Removed-Sphere Method},
+ author = {Ning, Zhenhua and Smirnov, A. V. and Shelton, William A. and Johnson, Duane D.},
+ date = {2022-12-12},
+ journaltitle = {Physical Review B},
+ shortjournal = {Phys. Rev. B},
+ volume = {106},
+ number = {23},
+ pages = {235114},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevB.106.235114},
+ url = {https://link.aps.org/doi/10.1103/PhysRevB.106.235114},
+ urldate = {2023-04-04},
+ abstract = {An efficient and accurate generalization of the removed-sphere method (RSM) to solve the Poisson equation for total charge density in a solid with space-filling convex Voronoi polyhedra (VPs) and any symmetry is presented. The generalized RSM avoids the use of multipoles and VP shape functions for cellular integrals, which have associated ill-convergent large, double-internal L sums in spherical-harmonic expansions, so that fast convergence in single-L sums is reached. Our RSM adopts full Ewald formulation to work for all configurations or when symmetry breaking occurs, such as for atomic displacements or elastic constant calculations. The structure-dependent coefficients AL that define RSM can be calculated once for a fixed structure and speed up the whole self-consistent-field procedure. The accuracy and rapid convergence properties are confirmed using two analytic models, including the Coulomb potential and energy. We then implement the full-potential RSM using the Green's function Korringa-Kohn-Rostoker (KKR) method for real applications and compare the results with other first-principle methods and experimental data, showing that they are equally as accurate.},
+ keywords = {/unread,DFT,KKR,Poisson equation},
+ file = {/Users/wasmer/Nextcloud/Zotero/Ning et al_2022_Full-potential KKR within the removed-sphere method.pdf}
+}
+
@article{novikovMagneticMomentTensor2022,
title = {Magnetic {{Moment Tensor Potentials}} for Collinear Spin-Polarized Materials Reproduce Different Magnetic States of Bcc {{Fe}}},
author = {Novikov, Ivan and Grabowski, Blazej and Körmann, Fritz and Shapeev, Alexander},
@@ -5954,6 +6734,27 @@
file = {/Users/wasmer/Nextcloud/Zotero/Novikov et al_2022_Magnetic Moment Tensor Potentials for collinear spin-polarized materials.pdf}
}
+@article{novikovMagneticMomentTensor2022a,
+ title = {Magnetic {{Moment Tensor Potentials}} for Collinear Spin-Polarized Materials Reproduce Different Magnetic States of Bcc {{Fe}}},
+ author = {Novikov, Ivan and Grabowski, Blazej and Körmann, Fritz and Shapeev, Alexander},
+ date = {2022-01-25},
+ journaltitle = {npj Computational Materials},
+ shortjournal = {npj Comput Mater},
+ volume = {8},
+ number = {1},
+ pages = {1--6},
+ publisher = {{Nature Publishing Group}},
+ issn = {2057-3960},
+ doi = {10.1038/s41524-022-00696-9},
+ url = {https://www.nature.com/articles/s41524-022-00696-9},
+ urldate = {2023-04-03},
+ abstract = {We present the magnetic Moment Tensor Potentials (mMTPs), a class of machine-learning interatomic potentials, accurately reproducing both vibrational and magnetic degrees of freedom as provided, e.g., from first-principles calculations. The accuracy is achieved by a two-step minimization scheme that coarse-grains the atomic and the spin space. The performance of the mMTPs is demonstrated for the prototype magnetic system bcc iron, with applications to phonon calculations for different magnetic states, and molecular-dynamics simulations with fluctuating magnetic moments.},
+ issue = {1},
+ langid = {english},
+ keywords = {ACE,AML,collinear,Ferromagnetism,FM,magnetism,MD,ML,MLP,mMTP,MTP,original publication,PAW,spin-dependent,spin-polarized,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Novikov et al_2022_Magnetic Moment Tensor Potentials for collinear spin-polarized materials2.pdf}
+}
+
@article{ohCompleteQuantumHall2013,
title = {The {{Complete Quantum Hall Trio}}},
author = {Oh, Seongshik},
@@ -6017,6 +6818,26 @@
file = {/Users/wasmer/Zotero/storage/6TZCQAXX/Machine_Learning_For_Physicists_2021.html}
}
+@article{otrokovPredictionObservationAntiferromagnetic2019,
+ title = {Prediction and Observation of an Antiferromagnetic Topological Insulator},
+ author = {Otrokov, M. M. and Klimovskikh, I. I. and Bentmann, H. and Estyunin, D. and Zeugner, A. and Aliev, Z. S. and Gaß, S. and Wolter, A. U. B. and Koroleva, A. V. and Shikin, A. M. and Blanco-Rey, M. and Hoffmann, M. and Rusinov, I. P. and Vyazovskaya, A. Yu and Eremeev, S. V. and Koroteev, Yu M. and Kuznetsov, V. M. and Freyse, F. and Sánchez-Barriga, J. and Amiraslanov, I. R. and Babanly, M. B. and Mamedov, N. T. and Abdullayev, N. A. and Zverev, V. N. and Alfonsov, A. and Kataev, V. and Büchner, B. and Schwier, E. F. and Kumar, S. and Kimura, A. and Petaccia, L. and Di Santo, G. and Vidal, R. C. and Schatz, S. and Kißner, K. and Ünzelmann, M. and Min, C. H. and Moser, Simon and Peixoto, T. R. F. and Reinert, F. and Ernst, A. and Echenique, P. M. and Isaeva, A. and Chulkov, E. V.},
+ date = {2019-12},
+ journaltitle = {Nature},
+ volume = {576},
+ number = {7787},
+ pages = {416--422},
+ publisher = {{Nature Publishing Group}},
+ issn = {1476-4687},
+ doi = {10.1038/s41586-019-1840-9},
+ url = {https://www.nature.com/articles/s41586-019-1840-9},
+ urldate = {2023-03-17},
+ abstract = {Magnetic topological insulators are narrow-gap semiconductor materials that combine non-trivial band topology and magnetic order1. Unlike their nonmagnetic counterparts, magnetic topological insulators may have some of the surfaces gapped, which enables a number of exotic phenomena that have potential applications in spintronics1, such as the quantum anomalous Hall effect2 and chiral Majorana fermions3. So far, magnetic topological insulators have only been created by means of doping nonmagnetic topological insulators with 3d transition-metal elements; however, such an approach leads to strongly inhomogeneous magnetic4 and electronic5 properties of these materials, restricting the observation of important effects to very low temperatures2,3. An intrinsic magnetic topological insulator—a stoichiometric well ordered magnetic compound—could be an ideal solution to these problems, but no such material has been observed so far. Here we predict by ab~initio calculations and further confirm using various experimental techniques the realization of an antiferromagnetic topological insulator in the layered van der Waals compound MnBi2Te4. The~antiferromagnetic ordering ~that MnBi2Te4 ~shows makes it invariant with respect to the~combination of the time-reversal and primitive-lattice translation symmetries, giving rise to a ℤ2 topological classification; ℤ2~=~1~for~MnBi2Te4, confirming its topologically nontrivial nature. Our experiments indicate that the symmetry-breaking (0001) surface of MnBi2Te4 exhibits a large bandgap in the topological surface state. We expect this property to eventually enable the observation of a number of fundamental phenomena, among them quantized magnetoelectric coupling6–8 and axion electrodynamics9,10. Other exotic phenomena could become accessible at much higher temperatures than those reached so far, such as the quantum anomalous Hall effect2 and chiral Majorana fermions3.},
+ issue = {7787},
+ langid = {english},
+ keywords = {/unread,ARPES,PGI-1/IAS-1 guests,topological insulator,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Otrokov et al_2019_Prediction and observation of an antiferromagnetic topological insulator.pdf}
+}
+
@article{ouyangSISSOCompressedsensingMethod2018,
title = {{{SISSO}}: {{A}} Compressed-Sensing Method for Identifying the Best Low-Dimensional Descriptor in an Immensity of Offered Candidates},
shorttitle = {{{SISSO}}},
@@ -6075,6 +6896,26 @@
file = {/Users/wasmer/Nextcloud/Zotero/Paleico_Behler_2021_A bin and hash method for analyzing reference data and descriptors in machine.pdf}
}
+@article{pantDFTaidedMachineLearningbased2023,
+ title = {{{DFT-aided}} Machine Learning-Based Discovery of Magnetism in {{Fe-based}} Bimetallic Chalcogenides},
+ author = {Pant, Dharmendra and Pokharel, Suresh and Mandal, Subhasish and Kc, Dukka B. and Pati, Ranjit},
+ date = {2023-02-25},
+ journaltitle = {Scientific Reports},
+ shortjournal = {Sci Rep},
+ volume = {13},
+ number = {1},
+ eprint = {36841922},
+ eprinttype = {pmid},
+ pages = {3277},
+ issn = {2045-2322},
+ doi = {10.1038/s41598-023-30438-w},
+ abstract = {With the technological advancement in recent years and the widespread use of magnetism in every sector of the current technology, a search for a low-cost magnetic material has been more important than ever. The discovery of magnetism in alternate materials such as metal chalcogenides with abundant atomic constituents would be a milestone in such a scenario. However, considering the multitude of possible chalcogenide configurations, predictive computational modeling or experimental synthesis is an open challenge. Here, we recourse to a stacked generalization machine learning model to predict magnetic moment (µB) in hexagonal Fe-based bimetallic chalcogenides, FexAyB; A represents Ni, Co, Cr, or Mn, and B represents S, Se, or Te, and x and y represent the concentration of respective atoms. The stacked generalization model is trained on the dataset obtained using first-principles density functional theory. The model achieves MSE, MAE, and R2 values of 1.655~(µB)2, 0.546~(µB), and 0.922 respectively on an independent test set, indicating that our model predicts the compositional dependent magnetism in bimetallic chalcogenides with a high degree of accuracy. A generalized algorithm is also developed to test the universality of our proposed model for any concentration of Ni, Co, Cr, or Mn up to 62.5\% in bimetallic chalcogenides.},
+ langid = {english},
+ pmcid = {PMC9968303},
+ keywords = {AML,ANN,chalcogenides,cross-validation,kernel methods,linear regression,magnetic moment,magnetism,materials,ML,model stacking,multi-model,PAW,prediction of magnetic moment,random forest,scikit-learn,spin-dependent,stack generalization,SVM,transition metals,VASP,with-code,XGB},
+ file = {/Users/wasmer/Nextcloud/Zotero/Pant et al_2023_DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic.pdf}
+}
+
@article{parsaeifardAssessmentStructuralResolution2021,
title = {An Assessment of the Structural Resolution of Various Fingerprints Commonly Used in Machine Learning},
author = {Parsaeifard, Behnam and De, Deb Sankar and Christensen, Anders S. and Faber, Felix A. and Kocer, Emir and De, Sandip and Behler, Jörg and family=Lilienfeld, given=O. Anatole, prefix=von, useprefix=false and Goedecker, Stefan},
@@ -6095,6 +6936,26 @@
file = {/Users/wasmer/Nextcloud/Zotero/Parsaeifard et al_2021_An assessment of the structural resolution of various fingerprints commonly.pdf}
}
+@article{parsaeifardAssessmentStructuralResolution2021a,
+ title = {An Assessment of the Structural Resolution of Various Fingerprints Commonly Used in Machine Learning},
+ author = {Parsaeifard, Behnam and De, Deb Sankar and Christensen, Anders S. and Faber, Felix A. and Kocer, Emir and De, Sandip and Behler, Jörg and family=Lilienfeld, given=O. Anatole, prefix=von, useprefix=false and Goedecker, Stefan},
+ date = {2021-04},
+ journaltitle = {Machine Learning: Science and Technology},
+ shortjournal = {Mach. Learn.: Sci. Technol.},
+ volume = {2},
+ number = {1},
+ pages = {015018},
+ publisher = {{IOP Publishing}},
+ issn = {2632-2153},
+ doi = {10.1088/2632-2153/abb212},
+ url = {https://dx.doi.org/10.1088/2632-2153/abb212},
+ urldate = {2023-03-19},
+ abstract = {Atomic environment fingerprints are widely used in computational materials science, from machine learning potentials to the quantification of similarities between atomic configurations. Many approaches to the construction of such fingerprints, also called structural descriptors, have been proposed. In this work, we compare the performance of fingerprints based on the overlap matrix, the smooth overlap of atomic positions, Behler–Parrinello atom-centered symmetry functions, modified Behler–Parrinello symmetry functions used in the ANI-1ccx potential and the Faber–Christensen–Huang–Lilienfeld fingerprint under various aspects. We study their ability to resolve differences in local environments and in particular examine whether there are certain atomic movements that leave the fingerprints exactly or nearly invariant. For this purpose, we introduce a sensitivity matrix whose eigenvalues quantify the effect of atomic displacement modes on the fingerprint. Further, we check whether these displacements correlate with the variation of localized physical quantities such as forces. Finally, we extend our examination to the correlation between molecular fingerprints obtained from the atomic fingerprints and global quantities of entire molecules.},
+ langid = {english},
+ keywords = {/unread,ACSF,AML,descriptor comparison,descriptors,descriptors analysis,FCHL,MBSF,MD,ML,OM descriptor,SOAP},
+ file = {/Users/wasmer/Zotero/storage/KIPWQ4LW/Parsaeifard et al. - 2021 - An assessment of the structural resolution of vari.pdf}
+}
+
@article{parsaeifardManifoldsQuasiconstantSOAP2022,
title = {Manifolds of Quasi-Constant {{SOAP}} and {{ACSF}} Fingerprints and the Resulting Failure to Machine Learn Four-Body Interactions},
author = {Parsaeifard, Behnam and Goedecker, Stefan},
@@ -6114,6 +6975,43 @@
file = {/Users/wasmer/Nextcloud/Zotero/Parsaeifard_Goedecker_2022_Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting.pdf}
}
+@article{parsaeifardManifoldsQuasiconstantSOAP2022a,
+ title = {Manifolds of Quasi-Constant {{SOAP}} and {{ACSF}} Fingerprints and the Resulting Failure to Machine Learn Four-Body Interactions},
+ author = {Parsaeifard, Behnam and Goedecker, Stefan},
+ date = {2022-01-21},
+ journaltitle = {The Journal of Chemical Physics},
+ shortjournal = {J. Chem. Phys.},
+ volume = {156},
+ number = {3},
+ pages = {034302},
+ publisher = {{American Institute of Physics}},
+ issn = {0021-9606},
+ doi = {10.1063/5.0070488},
+ url = {https://aip.scitation.org/doi/full/10.1063/5.0070488},
+ urldate = {2023-03-19},
+ abstract = {Atomic fingerprints are commonly used for the characterization of local environments of atoms in machine learning and other contexts. In this work, we study the behavior of two widely used fingerprints, namely, the smooth overlap of atomic positions (SOAP) and the atom-centered symmetry functions (ACSFs), under finite changes of atomic positions and demonstrate the existence of manifolds of quasi-constant fingerprints. These manifolds are found numerically by following eigenvectors of the sensitivity matrix with quasi-zero eigenvalues. The existence of such manifolds in ACSF and SOAP causes a failure to machine learn four-body interactions, such as torsional energies that are part of standard force fields. No such manifolds can be found for the overlap matrix (OM) fingerprint due to its intrinsic many-body character.},
+ keywords = {/unread,ACSF,AML,descriptor comparison,descriptors,descriptors analysis,incompleteness,Manifolds,ML,OM descriptor,SOAP},
+ file = {/Users/wasmer/Zotero/storage/ARZ5YYBV/Parsaeifard and Goedecker - 2022 - Manifolds of quasi-constant SOAP and ACSF fingerpr.pdf}
+}
+
+@article{pathrudkarMachineLearningBased2022,
+ title = {Machine Learning Based Prediction of the Electronic Structure of Quasi-One-Dimensional Materials under Strain},
+ author = {Pathrudkar, Shashank and Yu, Hsuan Ming and Ghosh, Susanta and Banerjee, Amartya S.},
+ date = {2022-05-26},
+ journaltitle = {Physical Review B},
+ shortjournal = {Phys. Rev. B},
+ volume = {105},
+ number = {19},
+ pages = {195141},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevB.105.195141},
+ url = {https://link.aps.org/doi/10.1103/PhysRevB.105.195141},
+ urldate = {2023-04-14},
+ abstract = {We present a machine learning based model that can predict the electronic structure of quasi-one-dimensional materials while they are subjected to deformation modes such as torsion and extension/compression. The technique described here applies to important classes of materials systems such as nanotubes, nanoribbons, nanowires, miscellaneous chiral structures, and nanoassemblies, for all of which, tuning the interplay of mechanical deformations and electronic fields, i.e., strain engineering, is an active area of investigation in the literature. Our model incorporates global structural symmetries and atomic relaxation effects, benefits from the use of helical coordinates to specify the electronic fields, and makes use of a specialized data generation process that solves the symmetry-adapted equations of Kohn-Sham density functional theory in these coordinates. Using armchair single-wall carbon nanotubes as a prototypical example, we demonstrate the use of the model to predict the fields associated with the ground-state electron density and the nuclear pseudocharges, when three parameters (namely, the radius of the nanotube, its axial stretch, and the twist per unit length) are specified as inputs. Other electronic properties of interest, including the ground-state electronic free energy, can be evaluated from these predicted fields with low-overhead postprocessing, typically to chemical accuracy. Additionally, we show how the nuclear coordinates can be reliably determined from the predicted pseudocharge field using a clustering-based technique. Remarkably, only about 120 data points are found to be enough to predict the three-dimensional electronic fields accurately, which we ascribe to the constraints imposed by symmetry in the problem setup, the use of low-discrepancy sequences for sampling, and efficient representation of the intrinsic low-dimensional features of the electronic fields. We comment on the interpretability of our machine learning model and anticipate that our framework will find utility in the automated discovery of low-dimensional materials, as well as the multiscale modeling of such systems.},
+ keywords = {1D,1D materials,AML,carbon,clustering,core electrons,DBSCAN,dimensionality reduction,dimensionality reduction of target,helical,helical coordinates,low-dimensional materials,ML,ML-DFT,ML-ESM,nanomaterials,NN,PCA,prediction of electron density,prediction of nuclear charges},
+ file = {/Users/wasmer/Nextcloud/Zotero/Pathrudkar et al_2022_Machine learning based prediction of the electronic structure of.pdf;/Users/wasmer/Zotero/storage/EH3KE7NL/PhysRevB.105.html}
+}
+
@unpublished{pedersonMachineLearningDensity2022,
title = {Machine Learning and Density Functional Theory},
author = {Pederson, Ryan and Kalita, Bhupalee and Burke, Kieron},
@@ -6255,18 +7153,54 @@
@article{poelkingBenchMLExtensiblePipelining2022,
title = {{{BenchML}}: An Extensible Pipelining Framework for Benchmarking Representations of Materials and Molecules at Scale},
shorttitle = {{{BenchML}}},
- author = {Poelking, Carl and Faber, Felix and Cheng, Bingqing},
- date = {2022},
+ author = {Poelking, Carl and Faber, Felix A. and Cheng, Bingqing},
+ date = {2022-11},
journaltitle = {Machine Learning: Science and Technology},
shortjournal = {Mach. Learn.: Sci. Technol.},
+ volume = {3},
+ number = {4},
+ pages = {040501},
+ publisher = {{IOP Publishing}},
issn = {2632-2153},
doi = {10.1088/2632-2153/ac4d11},
- url = {http://iopscience.iop.org/article/10.1088/2632-2153/ac4d11},
- urldate = {2022-05-09},
+ url = {https://dx.doi.org/10.1088/2632-2153/ac4d11},
+ urldate = {2023-03-19},
abstract = {We introduce a machine-learning (ML) framework for high-throughput benchmarking of diverse representations of chemical systems against datasets of materials and molecules. The guiding principle underlying the benchmarking approach is to evaluate raw descriptor performance by limiting model complexity to simple regression schemes while enforcing best ML practices, allowing for unbiased hyperparameter optimization, and assessing learning progress through learning curves along series of synchronized train-test splits. The resulting models are intended as baselines that can inform future method development, in addition to indicating how easily a given dataset can be learnt. Through a comparative analysis of the training outcome across a diverse set of physicochemical, topological and geometric representations, we glean insight into the relative merits of these representations as well as their interrelatedness.},
langid = {english},
- keywords = {descriptor comparison},
- file = {/Users/wasmer/Nextcloud/Zotero/Poelking et al_2022_BenchML.pdf}
+ keywords = {ACSF,AML,benchmarking,CM,Coulomb matrix,descriptor comparison,descriptors,DScribe,ECFP descriptor,GYLM descriptor,KRR,library,linear regression,materials,MBTR,ML,MLOps,molecules,QM7b,QM9,SISSO,SOAP,with-code,workflows},
+ file = {/Users/wasmer/Zotero/storage/QXAEL2PM/Poelking et al_2022_BenchML.pdf}
+}
+
+@online{polakExtractingAccurateMaterials2023,
+ title = {Extracting {{Accurate Materials Data}} from {{Research Papers}} with {{Conversational Language Models}} and {{Prompt Engineering}} -- {{Example}} of {{ChatGPT}}},
+ author = {Polak, Maciej P. and Morgan, Dane},
+ date = {2023-03-07},
+ eprint = {2303.05352},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2303.05352},
+ url = {http://arxiv.org/abs/2303.05352},
+ urldate = {2023-03-17},
+ abstract = {There has been a growing effort to replace hand extraction of data from research papers with automated data extraction based on natural language processing (NLP), language models (LMs), and recently, large language models (LLMs). Although these methods enable efficient extraction of data from large sets of research papers, they require a significant amount of up-front effort, expertise, and coding. In this work we propose the ChatExtract method that can fully automate very accurate data extraction with essentially no initial effort or background using an advanced conversational LLM (or AI). ChatExtract consists of a set of engineered prompts applied to a conversational LLM that both identify sentences with data, extract data, and assure its correctness through a series of follow-up questions. These follow-up questions address a critical challenge associated with LLMs - their tendency to provide factually inaccurate responses. ChatExtract can be applied with any conversational LLMs and yields very high quality data extraction. In tests on materials data we find precision and recall both over 90\% from the best conversational LLMs, likely rivaling or exceeding human accuracy in many cases. We demonstrate that the exceptional performance is enabled by the information retention in a conversational model combined with purposeful redundancy and introducing uncertainty through follow-up prompts. These results suggest that approaches similar to ChatExtract, due to their simplicity, transferability and accuracy are likely to replace other methods of data extraction in the near future.},
+ pubstate = {preprint},
+ keywords = {/unread,ChatGPT,data mining,database generation,GPT,GPT-3,literature analysis,LLM,materials,prompt engineering},
+ file = {/Users/wasmer/Nextcloud/Zotero/Polak_Morgan_2023_Extracting Accurate Materials Data from Research Papers with Conversational.pdf;/Users/wasmer/Zotero/storage/9HJ5N4FB/2303.html}
+}
+
+@online{polakFlexibleModelAgnosticMethod2023,
+ title = {Flexible, {{Model-Agnostic Method}} for {{Materials Data Extraction}} from {{Text Using General Purpose Language Models}}},
+ author = {Polak, Maciej P. and Modi, Shrey and Latosinska, Anna and Zhang, Jinming and Wang, Ching-Wen and Wang, Shanonan and Hazra, Ayan Deep and Morgan, Dane},
+ date = {2023-02-09},
+ eprint = {2302.04914},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2302.04914},
+ url = {http://arxiv.org/abs/2302.04914},
+ urldate = {2023-03-17},
+ abstract = {Accurate and comprehensive material databases extracted from research papers are critical for materials science and engineering but require significant human effort to develop. In this paper we present a simple method of extracting materials data from full texts of research papers suitable for quickly developing modest-sized databases. The method requires minimal to no coding, prior knowledge about the extracted property, or model training, and provides high recall and almost perfect precision in the resultant database. The method is fully automated except for one human-assisted step, which typically requires just a few hours of human labor. The method builds on top of natural language processing and large general language models but can work with almost any such model. The language models GPT-3/3.5, bart and DeBERTaV3 are evaluated here for comparison. We provide a detailed detailed analysis of the methods performance in extracting bulk modulus data, obtaining up to 90\% precision at 96\% recall, depending on the amount of human effort involved. We then demonstrate the methods broader effectiveness by developing a database of critical cooling rates for metallic glasses.},
+ pubstate = {preprint},
+ keywords = {ChatGPT,data mining,database generation,GPT,GPT-3,literature analysis,LLM,materials},
+ file = {/Users/wasmer/Nextcloud/Zotero/Polak et al_2023_Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using.pdf;/Users/wasmer/Zotero/storage/2BSBWMWC/2302.html}
}
@online{PossibleGameChanger,
@@ -6278,6 +7212,24 @@
file = {/Users/wasmer/Zotero/storage/9GDZNCPD/a-possible-game-changer-for-next-generation-microelectronics.html}
}
+@article{pozdnyakovFastGeneralTwo2023,
+ title = {Fast General Two- and Three-Body Interatomic Potential},
+ author = {Pozdnyakov, Sergey and Oganov, Artem R. and Mazhnik, Efim and Mazitov, Arslan and Kruglov, Ivan},
+ date = {2023-03-30},
+ journaltitle = {Physical Review B},
+ shortjournal = {Phys. Rev. B},
+ volume = {107},
+ number = {12},
+ pages = {125160},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevB.107.125160},
+ url = {https://link.aps.org/doi/10.1103/PhysRevB.107.125160},
+ urldate = {2023-04-02},
+ abstract = {We introduce a new class of machine learning interatomic potentials—fast general two- and three-body potential (GTTP), which is as fast as conventional empirical potentials and require computational time that remains constant with increasing fitting flexibility. GTTP does not contain any assumptions about the functional form of two- and three-body interactions. These interactions can be modeled arbitrarily accurately, potentially by thousands of parameters not affecting resulting computational cost. Time complexity is O(1) per every considered pair or triple of atoms. The fitting procedure is reduced to simple linear regression on ab initio calculated energies and forces and leads to effective two- and three-body potential, reproducing quantum many-body interactions as accurately as possible. Our potential can be made continuously differentiable any number of times at the expense of increased computational time. We made a number of performance tests on one-, two- and three-component systems. The flexibility of the introduced approach makes the potential transferable in terms of size and type of atomic systems as long as they involve the same atomic species. We show that trained on randomly generated structures with just eight atoms in the unit cell, it significantly outperforms common empirical interatomic potentials in the study of large systems, such as grain boundaries in polycrystalline materials.},
+ keywords = {ACE,Allegro,AML,binary systems,DeePMD-kit,defects,descriptors,DimeNet,EAM,GemNet,GTTP,invariance,LAMMPS,linear regression,MACE,materials,MD,ML,MLP,MTP,NequIP,original publication,PES,ternary systems,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Pozdnyakov et al_2023_Fast general two- and three-body interatomic potential.pdf;/Users/wasmer/Zotero/storage/E6VPDJ2T/PhysRevB.107.html}
+}
+
@article{pozdnyakovIncompletenessAtomicStructure2020,
title = {Incompleteness of {{Atomic Structure Representations}}},
author = {Pozdnyakov, Sergey N. and Willatt, Michael J. and Bartók, Albert P. and Ortner, Christoph and Csányi, Gábor and Ceriotti, Michele},
@@ -6309,6 +7261,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Pozdnyakov_Ceriotti_2022_Incompleteness of graph convolutional neural networks for points clouds in.pdf;/Users/wasmer/Zotero/storage/ZKHDUH3X/2201.html}
}
+@online{probstGrowingPainsReacting2022,
+ title = {Growing Pains: {{Reacting}} to Negative Impacts of Deep Learning on Machine Learning for Chemistry},
+ shorttitle = {Growing Pains},
+ author = {Probst, Daniel},
+ date = {2022-11-23},
+ eprinttype = {ChemRxiv},
+ doi = {10.26434/chemrxiv-2022-z6s5m},
+ url = {https://chemrxiv.org/engage/chemrxiv/article-details/637b6121082129d540ff5724},
+ urldate = {2023-04-10},
+ abstract = {While the introduction of practical deep learning has driven progress across scientific fields, recent research highlighted that deep learning has potential negative impacts on the scientific community and society as a whole. An ever-growing need for more computational resources may exacerbate the concentration of funding and the exclusiveness of research between countries, sectors, and institutions. Here, I introduce recent concerns and considerations of the machine learning research community and present potential solutions.},
+ langid = {english},
+ pubstate = {preprint},
+ keywords = {AML,best practices,chemistry,computational cost,cost analysis,criticism,Deep learning,LLM,ML,ML cost analysis,ML ethics,model evaluation,skepticism,small data},
+ file = {/Users/wasmer/Nextcloud/Zotero/Probst_2022_Growing pains.pdf}
+}
+
@article{prodanNearsightednessElectronicMatter2005,
title = {Nearsightedness of Electronic Matter},
author = {Prodan, E. and Kohn, W.},
@@ -6329,9 +7297,9 @@
title = {Atomic Cluster Expansion for Quantum-Accurate Large-Scale Simulations of Carbon},
author = {Qamar, Minaam and Mrovec, Matous and Lysogorskiy, Yury and Bochkarev, Anton and Drautz, Ralf},
date = {2022-10-25},
- number = {arXiv:2210.09161},
- eprint = {arXiv:2210.09161},
+ eprint = {2210.09161},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2210.09161},
url = {http://arxiv.org/abs/2210.09161},
urldate = {2023-01-20},
@@ -6354,7 +7322,6 @@
title = {Cracking the {{Quantum Scaling Limit}} with {{Machine Learned Electron Densities}}},
author = {Rackers, Joshua A. and Tecot, Lucas and Geiger, Mario and Smidt, Tess E.},
date = {2022-02-10},
- number = {arXiv:2201.03726},
eprint = {2201.03726},
eprinttype = {arxiv},
eprintclass = {cond-mat, physics:physics},
@@ -6371,9 +7338,9 @@
title = {Cracking the {{Quantum Scaling Limit}} with {{Machine Learned Electron Densities}}},
author = {Rackers, Joshua A. and Tecot, Lucas and Geiger, Mario and Smidt, Tess E.},
date = {2022-02-10},
- number = {arXiv:2201.03726},
- eprint = {arXiv:2201.03726},
+ eprint = {2201.03726},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2201.03726},
url = {http://arxiv.org/abs/2201.03726},
urldate = {2022-07-10},
@@ -6477,7 +7444,6 @@
shorttitle = {Differentiable {{Physics}}},
author = {Ramsundar, Bharath and Krishnamurthy, Dilip and Viswanathan, Venkatasubramanian},
date = {2021-09-14},
- number = {arXiv:2109.07573},
eprint = {2109.07573},
eprinttype = {arxiv},
eprintclass = {physics},
@@ -6512,9 +7478,9 @@
title = {Graph Neural Networks for Materials Science and Chemistry},
author = {Reiser, Patrick and Neubert, Marlen and Eberhard, André and Torresi, Luca and Zhou, Chen and Shao, Chen and Metni, Houssam and family=Hoesel, given=Clint, prefix=van, useprefix=true and Schopmans, Henrik and Sommer, Timo and Friederich, Pascal},
date = {2022-08-05},
- number = {arXiv:2208.09481},
- eprint = {arXiv:2208.09481},
+ eprint = {2208.09481},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
doi = {10.48550/arXiv.2208.09481},
url = {http://arxiv.org/abs/2208.09481},
urldate = {2022-09-27},
@@ -6685,7 +7651,7 @@
isbn = {9783958063365},
langid = {english},
keywords = {juKKR,KKR,PGI-1/IAS-1,thesis},
- file = {/Users/wasmer/Nextcloud/Zotero/Rüßmann_2018_Spin scattering of topologically protected electrons at defects3.pdf;/Users/wasmer/Zotero/storage/T7V45S9S/850306.html}
+ file = {/Users/wasmer/Nextcloud/Zotero/Rüßmann_2018_Spin scattering of topologically protected electrons at defects4.pdf;/Users/wasmer/Zotero/storage/T7V45S9S/850306.html}
}
@article{ryczkoDeepLearningDensityfunctional2019,
@@ -6720,6 +7686,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Saal et al_2013_Materials Design and Discovery with High-Throughput Density Functional Theory.pdf}
}
+@article{sadeghiMetricsMeasuringDistances2013,
+ title = {Metrics for Measuring Distances in Configuration Spaces},
+ author = {Sadeghi, Ali and Ghasemi, S. Alireza and Schaefer, Bastian and Mohr, Stephan and Lill, Markus A. and Goedecker, Stefan},
+ date = {2013-11-14},
+ journaltitle = {The Journal of Chemical Physics},
+ shortjournal = {J. Chem. Phys.},
+ volume = {139},
+ number = {18},
+ pages = {184118},
+ publisher = {{American Institute of Physics}},
+ issn = {0021-9606},
+ doi = {10.1063/1.4828704},
+ url = {https://aip.scitation.org/doi/10.1063/1.4828704},
+ urldate = {2023-03-19},
+ abstract = {In order to characterize molecular structures we introduce configurational fingerprint vectors which are counterparts of quantities used experimentally to identify structures. The Euclidean distance between the configurational fingerprint vectors satisfies the properties of a metric and can therefore safely be used to measure dissimilarities between configurations in the high dimensional configuration space. In particular we show that these metrics are a perfect and computationally cheap replacement for the root-mean-square distance (RMSD) when one has to decide whether two noise contaminated configurations are identical or not. We introduce a Monte Carlo approach to obtain the global minimum of the RMSD between configurations, which is obtained from a global minimization over all translations, rotations, and permutations of atomic indices.},
+ keywords = {/unread,AML,descriptors,distance metric,ML,molecules,OM descriptor,original publication,RMSD,similarity analysis,similarity measure},
+ file = {/Users/wasmer/Zotero/storage/YLQYEHWE/Sadeghi et al. - 2013 - Metrics for measuring distances in configuration s.pdf}
+}
+
@unpublished{samuelMachineLearningPipelines2020,
title = {Machine {{Learning Pipelines}}: {{Provenance}}, {{Reproducibility}} and {{FAIR Data Principles}}},
shorttitle = {Machine {{Learning Pipelines}}},
@@ -6788,6 +7773,55 @@
file = {/Users/wasmer/Nextcloud/Zotero/Sauceda et al_2021_BIGDML.pdf;/Users/wasmer/Zotero/storage/XVR5SBVI/2106.html}
}
+@online{schaafAccurateReactionBarriers2023,
+ title = {Accurate {{Reaction Barriers}} for {{Catalytic Pathways}}: {{An Automatic Training Protocol}} for {{Machine Learning Force Fields}}},
+ shorttitle = {Accurate {{Reaction Barriers}} for {{Catalytic Pathways}}},
+ author = {Schaaf, Lars and Fako, Edvin and De, Sandip and Schäfer, Ansgar and Csányi, Gábor},
+ date = {2023-01-24},
+ eprint = {2301.09931},
+ eprinttype = {arxiv},
+ eprintclass = {physics},
+ doi = {10.48550/arXiv.2301.09931},
+ url = {http://arxiv.org/abs/2301.09931},
+ urldate = {2023-04-13},
+ abstract = {In this study, we introduce an automatic training protocol for developing machine learning force fields (MLFFs) that can accurately determine reaction barriers for a given catalytic reaction pathway. The protocol is demonstrated through its application to the eleven-step hydrogenation of carbon dioxide to methanol over an indium oxide catalyst. The training set is iteratively expanded with active learning, using the model's uncertainty estimates to sample novel configurations that are chemically relevant. Our final force field obtains reaction barriers that are within 0.05 eV of those obtained through Density Functional Theory (DFT) calculations. Additionally, we examine two extrapolation tasks. Firstly, we demonstrate that with only a few extra single-point DFT calculations, we can accurately capture the adsorption energy for all eleven reaction intermediates on platinum-doped surfaces. Secondly, we show that MLFFs can be used to identify a wide range of low-energy adsorption configurations that are thermodynamically relevant. This abundance of adsorbate geometries highlights the need for fast and accurate alternatives to direct ab-initio simulations.},
+ pubstate = {preprint},
+ keywords = {active learning,active learning protocol,AML,chemistry,GAP,Gaussian process,GPR,iterative learning scheme,MACE,ML,ML-FF,MLP,SOAP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Schaaf et al_2023_Accurate Reaction Barriers for Catalytic Pathways.pdf;/Users/wasmer/Zotero/storage/LACJS8K5/2301.html}
+}
+
+@online{schaarschmidtLearnedForceFields2022,
+ title = {Learned {{Force Fields Are Ready For Ground State Catalyst Discovery}}},
+ author = {Schaarschmidt, Michael and Riviere, Morgane and Ganose, Alex M. and Spencer, James S. and Gaunt, Alexander L. and Kirkpatrick, James and Axelrod, Simon and Battaglia, Peter W. and Godwin, Jonathan},
+ date = {2022-09-26},
+ eprint = {2209.12466},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.2209.12466},
+ url = {http://arxiv.org/abs/2209.12466},
+ urldate = {2023-04-03},
+ abstract = {We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces from a learned potential yields structures with similar or lower energy to those relaxed using the RPBE functional in over 50\textbackslash\% of evaluated systems, despite the fact that the predicted forces differ significantly from the ground truth. This has the surprising implication that learned potentials may be ready for replacing DFT in challenging catalytic systems such as those found in the Open Catalyst 2020 dataset. Furthermore, we show that a force field trained on a locally harmonic energy surface with the same minima as a target DFT energy is also able to find lower or similar energy structures in over 50\textbackslash\% of cases. This ``Easy Potential'' converges in fewer steps than a standard model trained on true energies and forces, which further accelerates calculations. Its success illustrates a key point: learned potentials can locate energy minima even when the model has high force errors. The main requirement for structure optimisation is simply that the learned potential has the correct minima. Since learned potentials are fast and scale linearly with system size, our results open the possibility of quickly finding ground states for large systems.},
+ pubstate = {preprint},
+ keywords = {AML,Database,DeepMind,Easy Potential,GNN,Graph Net Simulator,Jax,ML,ML-DFT,ML-FF,MLP,MPNN,OC20,Open Catalyst,original publication,PES,structure relaxation},
+ file = {/Users/wasmer/Nextcloud/Zotero/Schaarschmidt et al_2022_Learned Force Fields Are Ready For Ground State Catalyst Discovery.pdf;/Users/wasmer/Zotero/storage/8QZN3D56/2209.html}
+}
+
+@online{scherbelaFoundationModelNeural2023,
+ title = {Towards a {{Foundation Model}} for {{Neural Network Wavefunctions}}},
+ author = {Scherbela, Michael and Gerard, Leon and Grohs, Philipp},
+ date = {2023-03-17},
+ eprint = {2303.09949},
+ eprinttype = {arxiv},
+ eprintclass = {physics},
+ doi = {10.48550/arXiv.2303.09949},
+ url = {http://arxiv.org/abs/2303.09949},
+ urldate = {2023-04-17},
+ abstract = {Deep neural networks have become a highly accurate and powerful wavefunction ansatz in combination with variational Monte Carlo methods for solving the electronic Schr\textbackslash "odinger equation. However, despite their success and favorable scaling, these methods are still computationally too costly for wide adoption. A significant obstacle is the requirement to optimize the wavefunction from scratch for each new system, thus requiring long optimization. In this work, we propose a novel neural network ansatz, which effectively maps uncorrelated, computationally cheap Hartree-Fock orbitals, to correlated, high-accuracy neural network orbitals. This ansatz is inherently capable of learning a single wavefunction across multiple compounds and geometries, as we demonstrate by successfully transferring a wavefunction model pre-trained on smaller fragments to larger compounds. Furthermore, we provide ample experimental evidence to support the idea that extensive pre-training of a such a generalized wavefunction model across different compounds and geometries could lead to a foundation wavefunction model. Such a model could yield high-accuracy ab-initio energies using only minimal computational effort for fine-tuning and evaluation of observables.},
+ pubstate = {preprint},
+ keywords = {AML,chemical species scaling problem,DeepErwin,equivariant,FermiNet,few-shot learning,foundation models,HFT,Many-body theory,ML,ML-ESM,ML-QM,ML-QMBP,molecules,MPNN,multi-species,PauliNet,PES,prediction of wavefunction,pretrained models,transfer learning,VMC},
+ file = {/Users/wasmer/Nextcloud/Zotero/Scherbela et al_2023_Towards a Foundation Model for Neural Network Wavefunctions.pdf;/Users/wasmer/Zotero/storage/YVXYKDB3/2303.html}
+}
+
@unpublished{scherbelaSolvingElectronicSchr2021,
title = {Solving the Electronic {{Schr}}\textbackslash "odinger Equation for Multiple Nuclear Geometries with Weight-Sharing Deep Neural Networks},
author = {Scherbela, Michael and Reisenhofer, Rafael and Gerard, Leon and Marquetand, Philipp and Grohs, Philipp},
@@ -6843,6 +7877,57 @@
file = {/Users/wasmer/Nextcloud/Zotero/Schlenz_Sandfeld_2022_Applications of Machine Learning to the Study of Crystalline Materials.pdf}
}
+@article{schmidtCrystalGraphAttention2021,
+ title = {Crystal Graph Attention Networks for the Prediction of Stable Materials},
+ author = {Schmidt, Jonathan and Pettersson, Love and Verdozzi, Claudio and Botti, Silvana and Marques, Miguel A. L.},
+ date = {2021-12-03},
+ journaltitle = {Science Advances},
+ volume = {7},
+ number = {49},
+ pages = {eabi7948},
+ publisher = {{American Association for the Advancement of Science}},
+ doi = {10.1126/sciadv.abi7948},
+ url = {https://www.science.org/doi/10.1126/sciadv.abi7948},
+ urldate = {2023-04-04},
+ abstract = {Graph neural networks for crystal structures typically use the atomic positions and the atomic species as input. Unfortunately, this information is not available when predicting new materials, for which the precise geometrical information is unknown. We circumvent this problem by replacing the precise bond distances with embeddings of graph distances. This allows our networks to be applied directly in high-throughput studies based on both composition and crystal structure prototype without using relaxed structures as input. To train these networks, we curate a dataset of over 2 million density functional calculations of crystals with consistent calculation parameters. We apply the resulting model to the high-throughput search of 15 million tetragonal perovskites of composition ABCD2. As a result, we identify several thousand potentially stable compounds and demonstrate that transfer learning from the newly curated dataset reduces the required training data by 50\%.},
+ keywords = {AFLOW,AML,attention,CGAT,convex hull,crystal graph,crystal structure,GATN,library,materials discovery,materials project,MEGNet,ML,MPNN,multi-component systems,OQMD,original publication,perovskites,prediction from composition,prediction of structure,thermodynamic stability,transfer learning},
+ file = {/Users/wasmer/Nextcloud/Zotero/Schmidt et al_2021_Crystal graph attention networks for the prediction of stable materials.pdf}
+}
+
+@online{schmidtLargescaleMachinelearningassistedExploration2022,
+ title = {Large-Scale Machine-Learning-Assisted Exploration of the Whole Materials Space},
+ author = {Schmidt, Jonathan and Hoffmann, Noah and Wang, Hai-Chen and Borlido, Pedro and Carriço, Pedro J. M. A. and Cerqueira, Tiago F. T. and Botti, Silvana and Marques, Miguel A. L.},
+ date = {2022-10-02},
+ eprint = {2210.00579},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.2210.00579},
+ url = {http://arxiv.org/abs/2210.00579},
+ urldate = {2023-04-04},
+ abstract = {Crystal-graph attention networks have emerged recently as remarkable tools for the prediction of thermodynamic stability and materials properties from unrelaxed crystal structures. Previous networks trained on two million materials exhibited, however, strong biases originating from underrepresented chemical elements and structural prototypes in the available data. We tackled this issue computing additional data to provide better balance across both chemical and crystal-symmetry space. Crystal-graph networks trained with this new data show unprecedented generalization accuracy, and allow for reliable, accelerated exploration of the whole space of inorganic compounds. We applied this universal network to perform machine-learning assisted high-throughput materials searches including 2500 binary and ternary structure prototypes and spanning about 1 billion compounds. After validation using density-functional theory, we uncover in total 19512 additional materials on the convex hull of thermodynamic stability and \textasciitilde 150000 compounds with a distance of less than 50 meV/atom from the hull. Combining again machine learning and ab-initio methods, we finally evaluate the discovered materials for applications as superconductors, superhard materials, and we look for candidates with large gap deformation potentials, finding several compounds with extreme values of these properties.},
+ pubstate = {preprint},
+ keywords = {AML,atomate,CGAT,convex hull,crystal graph,crystal structure,crystal structure prediction,database generation,GAT,GATN,HTC,materials discovery,ML,MPNN,PBE,perovskites,polymorphs,prediction of Curie temperature,prediction of structure,superconductor,ternary systems,thermodynamic stability,transfer learning,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Schmidt et al_2022_Large-scale machine-learning-assisted exploration of the whole materials space.pdf;/Users/wasmer/Zotero/storage/Z7LCYKCS/2210.html}
+}
+
+@article{schmidtLearningModelsElectron2018,
+ title = {Learning Models for Electron Densities with {{Bayesian}} Regression},
+ author = {Schmidt, Eric and Fowler, Andrew T. and Elliott, James A. and Bristowe, Paul D.},
+ date = {2018-06-15},
+ journaltitle = {Computational Materials Science},
+ shortjournal = {Computational Materials Science},
+ volume = {149},
+ pages = {250--258},
+ issn = {0927-0256},
+ doi = {10.1016/j.commatsci.2018.03.029},
+ url = {https://www.sciencedirect.com/science/article/pii/S0927025618301824},
+ urldate = {2023-03-20},
+ abstract = {The Hohenberg-Kohn theorems posit the ground state electron density as a property of fundamental importance in condensed matter physics, finding widespread application in much of solid state physics in the form of density functional theory (DFT) and, at least in principle, in semi-empirical potentials such as the Embedded Atom Method (EAM). Using machine learning algorithms based on parametric linear models, we propose a systematic approach to developing such potentials for binary alloys based on DFT electron densities, as well as energies and forces. The approach is demonstrated on the technologically important Al-Ni alloy system. We further demonstrate how ground state electron densities, obtained with DFT, can be predicted such that total energies have an accuracy of order meV\,atom−1 for crystalline structures. The set of crystalline structures includes a range of materials representing different phases and bonding types, from Al structures to single-wall carbon nanotubes.},
+ langid = {english},
+ keywords = {Bayesian regression,CASTEP,defects,DFT,EAM,EM algorithm,genetic algorithm,invariance,linear regression,materials,MD,ML-DFT,ML-ESM,MLP,OF-DFT,prediction of electron density,RVM},
+ file = {/Users/wasmer/Zotero/storage/WIL72H29/Schmidt et al. - 2018 - Learning models for electron densities with Bayesi.pdf;/Users/wasmer/Zotero/storage/EJZSRRBA/S0927025618301824.html}
+}
+
@article{schmidtMachineLearningPhysical2019,
title = {Machine {{Learning}} the {{Physical Nonlocal Exchange}}–{{Correlation Functional}} of {{Density-Functional Theory}}},
author = {Schmidt, Jonathan and Benavides-Riveros, Carlos L. and Marques, Miguel A. L.},
@@ -6963,9 +8048,9 @@
shorttitle = {{{SchNetPack}} 2.0},
author = {Schütt, Kristof T. and Hessmann, Stefaan S. P. and Gebauer, Niklas W. A. and Lederer, Jonas and Gastegger, Michael},
date = {2022-12-11},
- number = {arXiv:2212.05517},
- eprint = {arXiv:2212.05517},
+ eprint = {2212.05517},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.2212.05517},
url = {http://arxiv.org/abs/2212.05517},
urldate = {2022-12-27},
@@ -7017,9 +8102,9 @@
title = {Physics-{{Informed Neural Networks}} as {{Solvers}} for the {{Time-Dependent Schr}}\textbackslash "odinger {{Equation}}},
author = {Shah, Karan and Stiller, Patrick and Hoffmann, Nico and Cangi, Attila},
date = {2022-10-22},
- number = {arXiv:2210.12522},
- eprint = {arXiv:2210.12522},
+ eprint = {2210.12522},
eprinttype = {arxiv},
+ eprintclass = {quant-ph},
doi = {10.48550/arXiv.2210.12522},
url = {http://arxiv.org/abs/2210.12522},
urldate = {2023-02-15},
@@ -7029,19 +8114,37 @@
file = {/Users/wasmer/Nextcloud/Zotero/Shah et al_2022_Physics-Informed Neural Networks as Solvers for the Time-Dependent.pdf;/Users/wasmer/Zotero/storage/NSJSIKTH/2210.html}
}
+@article{shapeevAccurateRepresentationFormation2017,
+ title = {Accurate Representation of Formation Energies of Crystalline Alloys with Many Components},
+ author = {Shapeev, A.},
+ date = {2017-11-01},
+ journaltitle = {Computational Materials Science},
+ shortjournal = {Computational Materials Science},
+ volume = {139},
+ pages = {26--30},
+ issn = {0927-0256},
+ doi = {10.1016/j.commatsci.2017.07.010},
+ url = {https://www.sciencedirect.com/science/article/pii/S0927025617303610},
+ urldate = {2023-04-04},
+ abstract = {In this paper I propose a new model for representing the formation energies of multicomponent crystalline alloys as a function of atom types. In the cases when displacements of atoms from their equilibrium positions are not large, the proposed method has a similar accuracy as the state-of-the-art cluster expansion method, and a better accuracy when the fitting dataset size is small. The proposed model has only two tunable parameters—one for the interaction range and one for the interaction complexity.},
+ langid = {english},
+ keywords = {alloys,AML,cluster expansion,high-entropy alloys,LRP,ML,MLP,n-ary alloys,original publication,prediction of energy,transition metals},
+ file = {/Users/wasmer/Nextcloud/Zotero/Shapeev_2017_Accurate representation of formation energies of crystalline alloys with many.pdf;/Users/wasmer/Zotero/storage/EQYE3F3F/S0927025617303610.html}
+}
+
@online{shenRepresentationindependentElectronicCharge2021,
title = {A Representation-Independent Electronic Charge Density Database for Crystalline Materials},
author = {Shen, Jimmy-Xuan and Munro, Jason M. and Horton, Matthew K. and Huck, Patrick and Dwaraknath, Shyam and Persson, Kristin A.},
date = {2021-07-07},
- number = {arXiv:2107.03540},
- eprint = {arXiv:2107.03540},
+ eprint = {2107.03540},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2107.03540},
url = {http://arxiv.org/abs/2107.03540},
urldate = {2022-12-31},
abstract = {In addition to being the core quantity in density functional theory, the charge density can be used in many tertiary analyses in materials sciences from bonding to assigning charge to specific atoms. The charge density is data-rich since it contains information about all the electrons in the system. With increasing utilization of machine-learning tools in materials sciences, a data-rich object like the charge density can be utilized in a wide range of applications. The database presented here provides a modern and user-friendly interface for a large and continuously updated collection of charge densities as part of the Materials Project. In addition to the charge density data, we provide the theory and code for changing the representation of the charge density which should enable more advanced machine-learning studies for the broader community.},
pubstate = {preprint},
- keywords = {_tablet,/unread,charge density,data repositories,Database,dimensionality reduction of target,electronic structure,library,materials,materials database,materials project,ML,ML-DFT,prediction from density,prediction of electron density,with-code},
+ keywords = {_tablet,charge density,data repositories,Database,dimensionality reduction of target,electronic structure,grid-based descriptors,library,materials,materials database,materials project,ML,ML-DFT,prediction from density,prediction of electron density,pseudopotential,representation of density,VASP,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Shen et al_2021_A representation-independent electronic charge density database for crystalline.pdf;/Users/wasmer/Zotero/storage/9A3MUVVK/2107.html}
}
@@ -7196,9 +8299,9 @@
title = {{{3DSC}} - {{A New Dataset}} of {{Superconductors Including Crystal Structures}}},
author = {Sommer, Timo and Willa, Roland and Schmalian, Jörg and Friederich, Pascal},
date = {2022-12-14},
- number = {arXiv:2212.06071},
- eprint = {arXiv:2212.06071},
+ eprint = {2212.06071},
eprinttype = {arxiv},
+ eprintclass = {cond-mat},
doi = {10.48550/arXiv.2212.06071},
url = {http://arxiv.org/abs/2212.06071},
urldate = {2023-02-15},
@@ -7242,9 +8345,9 @@
title = {Better, {{Faster Fermionic Neural Networks}}},
author = {Spencer, James S. and Pfau, David and Botev, Aleksandar and Foulkes, W. M. C.},
date = {2020-11-13},
- number = {arXiv:2011.07125},
- eprint = {arXiv:2011.07125},
+ eprint = {2011.07125},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.2011.07125},
url = {http://arxiv.org/abs/2011.07125},
urldate = {2022-06-25},
@@ -7399,9 +8502,9 @@
shorttitle = {{{MEGAN}}},
author = {Teufel, Jonas and Torresi, Luca and Reiser, Patrick and Friederich, Pascal},
date = {2022-11-23},
- number = {arXiv:2211.13236},
- eprint = {arXiv:2211.13236},
+ eprint = {2211.13236},
eprinttype = {arxiv},
+ eprintclass = {cs},
doi = {10.48550/arXiv.2211.13236},
url = {http://arxiv.org/abs/2211.13236},
urldate = {2023-03-02},
@@ -7482,12 +8585,29 @@
file = {/Users/wasmer/Nextcloud/Zotero/Thompson et al_2015_Spectral neighbor analysis method for automated generation of quantum-accurate.pdf}
}
+@article{thompsonSpectralNeighborAnalysis2015a,
+ title = {Spectral Neighbor Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials},
+ author = {Thompson, A. P. and Swiler, L. P. and Trott, C. R. and Foiles, S. M. and Tucker, G. J.},
+ date = {2015-03-15},
+ journaltitle = {Journal of Computational Physics},
+ shortjournal = {Journal of Computational Physics},
+ volume = {285},
+ pages = {316--330},
+ issn = {0021-9991},
+ doi = {10.1016/j.jcp.2014.12.018},
+ url = {https://www.sciencedirect.com/science/article/pii/S0021999114008353},
+ urldate = {2023-04-04},
+ abstract = {We present a new interatomic potential for solids and liquids called Spectral Neighbor Analysis Potential (SNAP). The SNAP potential has a very general form and uses machine-learning techniques to reproduce the energies, forces, and stress tensors of a large set of small configurations of atoms, which are obtained using high-accuracy quantum electronic structure (QM) calculations. The local environment of each atom is characterized by a set of bispectrum components of the local neighbor density projected onto a basis of hyperspherical harmonics in four dimensions. The bispectrum components are the same bond-orientational order parameters employed by the GAP potential [1]. The SNAP potential, unlike GAP, assumes a linear relationship between atom energy and bispectrum components. The linear SNAP coefficients are determined using weighted least-squares linear regression against the full QM training set. This allows the SNAP potential to be fit in a robust, automated manner to large QM data sets using many bispectrum components. The calculation of the bispectrum components and the SNAP potential are implemented in the LAMMPS parallel molecular dynamics code. We demonstrate that a previously unnoticed symmetry property can be exploited to reduce the computational cost of the force calculations by more than one order of magnitude. We present results for a SNAP potential for tantalum, showing that it accurately reproduces a range of commonly calculated properties of both the crystalline solid and the liquid phases. In addition, unlike simpler existing potentials, SNAP correctly predicts the energy barrier for screw dislocation migration in BCC tantalum.},
+ langid = {english},
+ keywords = {AML,bispectrum,descriptors,GAP,library,ML,MLP,optimization,original publication,SNAP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Thompson et al_2015_Spectral neighbor analysis method for automated generation of quantum-accurate2.pdf;/Users/wasmer/Zotero/storage/DIRR439L/S0021999114008353.html}
+}
+
@unpublished{togoSpglibSoftwareLibrary2018,
title = {Spglib: A Software Library for Crystal Symmetry Search},
shorttitle = {\$\textbackslash texttt\{\vphantom\}{{Spglib}}\vphantom\{\}\$},
author = {Togo, Atsushi and Tanaka, Isao},
date = {2018-08-05},
- number = {arXiv:1808.01590},
eprint = {1808.01590},
eprinttype = {arxiv},
eprintclass = {cond-mat},
@@ -7556,6 +8676,41 @@
file = {/Users/wasmer/Nextcloud/Zotero/Townsend_Vogiatzis_2019_Data-Driven Acceleration of the Coupled-Cluster Singles and Doubles Iterative.pdf;/Users/wasmer/Zotero/storage/RVTRBAZI/acs.jpclett.html}
}
+@online{tranMethodsComparingUncertainty2020,
+ title = {Methods for Comparing Uncertainty Quantifications for Material Property Predictions},
+ author = {Tran, Kevin and Neiswanger, Willie and Yoon, Junwoong and Zhang, Qingyang and Xing, Eric and Ulissi, Zachary W.},
+ date = {2020-02-20},
+ eprint = {1912.10066},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.1912.10066},
+ url = {http://arxiv.org/abs/1912.10066},
+ urldate = {2023-04-11},
+ abstract = {Data science and informatics tools have been proliferating recently within the computational materials science and catalysis fields. This proliferation has spurned the creation of various frameworks for automated materials screening, discovery, and design. Underpinning these frameworks are surrogate models with uncertainty estimates on their predictions. These uncertainty estimates are instrumental for determining which materials to screen next, but the computational catalysis field does not yet have a standard procedure for judging the quality of such uncertainty estimates. Here we present a suite of figures and performance metrics derived from the machine learning community that can be used to judge the quality of such uncertainty estimates. This suite probes the accuracy, calibration, and sharpness of a model quantitatively. We then show a case study where we judge various methods for predicting density-functional-theory-calculated adsorption energies. Of the methods studied here, we find that the best performer is a model where a convolutional neural network is used to supply features to a Gaussian process regressor, which then makes predictions of adsorption energies along with corresponding uncertainty estimates.},
+ pubstate = {preprint},
+ keywords = {active learning,AML,Bayesian methods,Gaussian process,materials,ML,regression,uncertainty quantification},
+ file = {/Users/wasmer/Nextcloud/Zotero/Tran et al_2020_Methods for comparing uncertainty quantifications for material property.pdf;/Users/wasmer/Zotero/storage/6RLGREQU/1912.html}
+}
+
+@article{tsubakiQuantumDeepField2020,
+ title = {Quantum {{Deep Field}}: {{Data-Driven Wave Function}}, {{Electron Density Generation}}, and {{Atomization Energy Prediction}} and {{Extrapolation}} with {{Machine Learning}}},
+ shorttitle = {Quantum {{Deep Field}}},
+ author = {Tsubaki, Masashi and Mizoguchi, Teruyasu},
+ date = {2020-11-10},
+ journaltitle = {Physical Review Letters},
+ shortjournal = {Phys. Rev. Lett.},
+ volume = {125},
+ number = {20},
+ pages = {206401},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevLett.125.206401},
+ url = {https://link.aps.org/doi/10.1103/PhysRevLett.125.206401},
+ urldate = {2023-04-11},
+ abstract = {Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn-Sham density functional theory (KS-DFT). Although this prediction is fast and accurate, we believe that a DNN model for KS-DFT must not only predict the properties but also provide the electron density of a molecule. This Letter presents the quantum deep field (QDF), which provides the electron density with an unsupervised but end-to-end physics-informed modeling by learning the atomization energy on a large-scale dataset. QDF performed well at atomization energy prediction, generated valid electron density, and demonstrated extrapolation.},
+ keywords = {AML,B3LYP,DTNN,GNN,library,Mayavi,ML,ML-DFT,ML-ESM,ML-QM,molecules,prediction of electron density,prediction of energy,prediction of external potential,prediction of wavefunction,SchNet,SchNetPack,visualization},
+ file = {/Users/wasmer/Nextcloud/Zotero/Tsubaki_Mizoguchi_2020_Quantum Deep Field.pdf;/Users/wasmer/Zotero/storage/U2B2LBDQ/PhysRevLett.125.html}
+}
+
@article{uhrinWorkflowsAiiDAEngineering2021,
title = {Workflows in {{AiiDA}}: {{Engineering}} a High-Throughput, Event-Based Engine for Robust and Modular Computational Workflows},
shorttitle = {Workflows in {{AiiDA}}},
@@ -7620,19 +8775,40 @@
file = {/Users/wasmer/Nextcloud/Zotero/Unke et al_2021_SE(3)-equivariant prediction of molecular wavefunctions and electronic densities.pdf}
}
+@article{vandermauseActiveLearningReactive2022,
+ title = {Active Learning of Reactive {{Bayesian}} Force Fields Applied to Heterogeneous Catalysis Dynamics of {{H}}/{{Pt}}},
+ author = {Vandermause, Jonathan and Xie, Yu and Lim, Jin Soo and Owen, Cameron J. and Kozinsky, Boris},
+ date = {2022-09-02},
+ journaltitle = {Nature Communications},
+ shortjournal = {Nat Commun},
+ volume = {13},
+ number = {1},
+ pages = {5183},
+ publisher = {{Nature Publishing Group}},
+ issn = {2041-1723},
+ doi = {10.1038/s41467-022-32294-0},
+ url = {https://www.nature.com/articles/s41467-022-32294-0},
+ urldate = {2023-04-11},
+ abstract = {Atomistic modeling of chemically reactive systems has so far relied on either expensive ab initio methods or bond-order force fields requiring arduous parametrization. Here, we describe a Bayesian active learning framework for autonomous “on-the-fly†training of fast and accurate reactive many-body force fields during molecular dynamics simulations. At each time-step, predictive uncertainties of a sparse Gaussian process are evaluated to automatically determine whether additional ab initio training data are needed. We introduce a general method for mapping trained kernel models onto equivalent polynomial models whose prediction cost is much lower and independent of the training set size. As a demonstration, we perform direct two-phase simulations of heterogeneous H2 turnover on the Pt(111) catalyst surface at chemical accuracy. The model trains itself in three days and performs at twice the speed of a ReaxFF model, while maintaining much higher fidelity to DFT and excellent agreement with experiment.},
+ issue = {1},
+ langid = {english},
+ keywords = {/unread,active learning,active learning online,AML,Bayesian methods,FLARE,Gaussian process,GPR,iterative learning,library,MD,ML,MLP,uncertainty quantification,with-code},
+ file = {/Users/wasmer/Nextcloud/Zotero/Vandermause et al_2022_Active learning of reactive Bayesian force fields applied to heterogeneous.pdf}
+}
+
@online{vanderoordHyperactiveLearningHAL2022,
title = {Hyperactive {{Learning}} ({{HAL}}) for {{Data-Driven Interatomic Potentials}}},
author = {family=Oord, given=Cas, prefix=van der, useprefix=true and Sachs, Matthias and Kovács, Dávid Péter and Ortner, Christoph and Csányi, Gábor},
date = {2022-11-07},
- number = {arXiv:2210.04225},
- eprint = {arXiv:2210.04225},
+ eprint = {2210.04225},
eprinttype = {arxiv},
+ eprintclass = {physics, stat},
doi = {10.48550/arXiv.2210.04225},
url = {http://arxiv.org/abs/2210.04225},
urldate = {2023-02-05},
abstract = {Data-driven interatomic potentials have emerged as a powerful class of surrogate models for \{\textbackslash it ab initio\} potential energy surfaces that are able to reliably predict macroscopic properties with experimental accuracy. In generating accurate and transferable potentials the most time-consuming and arguably most important task is generating the training set, which still requires significant expert user input. To accelerate this process, this work presents \textbackslash text\{\textbackslash it hyperactive learning\} (HAL), a framework for formulating an accelerated sampling algorithm specifically for the task of training database generation. The key idea is to start from a physically motivated sampler (e.g., molecular dynamics) and add a biasing term that drives the system towards high uncertainty and thus to unseen training configurations. Building on this framework, general protocols for building training databases for alloys and polymers leveraging the HAL framework will be presented. For alloys, ACE potentials for AlSi10 are created by fitting to a minimal HAL-generated database containing 88 configurations (32 atoms each) with fast evaluation times of {$<$}100 microsecond/atom/cpu-core. These potentials are demonstrated to predict the melting temperature with excellent accuracy. For polymers, a HAL database is built using ACE, able to determine the density of a long polyethylene glycol (PEG) polymer formed of 200 monomer units with experimental accuracy by only fitting to small isolated PEG polymers with sizes ranging from 2 to 32.},
pubstate = {preprint},
- keywords = {/unread,Physics - Computational Physics,Statistics - Machine Learning},
+ keywords = {ACE,active learning,Bayesian methods,Bayesian optimization,Bayesian regression,database generation,HAL,HAL-MD,iterative learning,iterative learning scheme,MD,MD17,uncertainty quantification},
file = {/Users/wasmer/Zotero/storage/4S2GHGVG/van der Oord et al. - 2022 - Hyperactive Learning (HAL) for Data-Driven Interat.pdf;/Users/wasmer/Zotero/storage/YJBLUYLE/2210.html}
}
@@ -7744,6 +8920,22 @@
file = {/Users/wasmer/Zotero/storage/86UUIB6S/S000926141400147X.html}
}
+@online{vonglehnSelfAttentionAnsatzAbinitio2022,
+ title = {A {{Self-Attention Ansatz}} for {{Ab-initio Quantum Chemistry}}},
+ author = {family=Glehn, given=Ingrid, prefix=von, useprefix=true and Spencer, James S. and Pfau, David},
+ date = {2022-11-24},
+ eprint = {2211.13672},
+ eprinttype = {arxiv},
+ eprintclass = {physics},
+ doi = {10.48550/arXiv.2211.13672},
+ url = {http://arxiv.org/abs/2211.13672},
+ urldate = {2023-04-17},
+ abstract = {We present a novel neural network architecture using self-attention, the Wavefunction Transformer (Psiformer), which can be used as an approximation (or Ansatz) for solving the many-electron Schr\textbackslash "odinger equation, the fundamental equation for quantum chemistry and material science. This equation can be solved from first principles, requiring no external training data. In recent years, deep neural networks like the FermiNet and PauliNet have been used to significantly improve the accuracy of these first-principle calculations, but they lack an attention-like mechanism for gating interactions between electrons. Here we show that the Psiformer can be used as a drop-in replacement for these other neural networks, often dramatically improving the accuracy of the calculations. On larger molecules especially, the ground state energy can be improved by dozens of kcal/mol, a qualitative leap over previous methods. This demonstrates that self-attention networks can learn complex quantum mechanical correlations between electrons, and are a promising route to reaching unprecedented accuracy in chemical calculations on larger systems.},
+ pubstate = {preprint},
+ keywords = {AML,attention,CCSD(T),DeepMind,FermiNet,JAX,Many-body theory,ML,ML-ESM,ML-QM,ML-QMBP,molecules,PauliNet,prediction of wavefunction,Psiformer,QMC,Quantum chemistry,self-attention,Slater-Jastrow,transfer learning,transformer,VMC},
+ file = {/Users/wasmer/Nextcloud/Zotero/von Glehn et al_2022_A Self-Attention Ansatz for Ab-initio Quantum Chemistry.pdf;/Users/wasmer/Zotero/storage/DJD69694/2211.html}
+}
+
@article{voskoAccurateSpindependentElectron1980,
title = {Accurate Spin-Dependent Electron Liquid Correlation Energies for Local Spin Density Calculations: A Critical Analysis},
shorttitle = {Accurate Spin-Dependent Electron Liquid Correlation Energies for Local Spin Density Calculations},
@@ -7800,9 +8992,9 @@
title = {Graph {{Nets}} for {{Partial Charge Prediction}}},
author = {Wang, Yuanqing and Fass, Josh and Stern, Chaya D. and Luo, Kun and Chodera, John},
date = {2019-09-17},
- number = {arXiv:1909.07903},
- eprint = {arXiv:1909.07903},
+ eprint = {1909.07903},
eprinttype = {arxiv},
+ eprintclass = {physics},
doi = {10.48550/arXiv.1909.07903},
url = {http://arxiv.org/abs/1909.07903},
urldate = {2022-09-27},
@@ -7812,6 +9004,27 @@
file = {/Users/wasmer/Nextcloud/Zotero/Wang et al_2019_Graph Nets for Partial Charge Prediction.pdf;/Users/wasmer/Zotero/storage/5MD2WVP3/1909.html}
}
+@article{wangLargeScaleDataset2022,
+ title = {Large Scale Dataset of Real Space Electronic Charge Density of Cubic Inorganic Materials from Density Functional Theory ({{DFT}}) Calculations},
+ author = {Wang, Fancy Qian and Choudhary, Kamal and Liu, Yu and Hu, Jianjun and Hu, Ming},
+ date = {2022-02-21},
+ journaltitle = {Scientific Data},
+ shortjournal = {Sci Data},
+ volume = {9},
+ number = {1},
+ pages = {59},
+ publisher = {{Nature Publishing Group}},
+ issn = {2052-4463},
+ doi = {10.1038/s41597-022-01158-z},
+ url = {https://www.nature.com/articles/s41597-022-01158-z},
+ urldate = {2023-04-14},
+ abstract = {Driven by the big data science, material informatics has attracted enormous research interests recently along with many recognized achievements. To acquire knowledge of materials by previous experience, both feature descriptors and databases are essential for training machine learning (ML) models with high accuracy. In this regard, the electronic charge density Ï(r), which in principle determines the properties of materials at their ground state, can be considered as one of the most appropriate descriptors. However, the systematic electronic charge density Ï(r) database of inorganic materials is still in its infancy due to the difficulties in collecting raw data in experiment and the expensive first-principles based computational cost in theory. Herein, a real space electronic charge density Ï(r) database of 17,418 cubic inorganic materials is constructed by performing high-throughput density functional theory calculations. The displayed Ï(r) patterns show good agreements with those reported in previous studies, which validates our computations. Further statistical analysis reveals that it possesses abundant and diverse data, which could accelerate Ï(r) related machine learning studies. Moreover, the electronic charge density database will also assists chemical bonding identifications and promotes new crystal discovery in experiments.},
+ issue = {1},
+ langid = {english},
+ keywords = {/unread,binary systems,Carolina Materials Database,Database,database of electron density,Heusler,inorganic materials,materials,materials project,prediction of electron density,quaternary systems,ternary systems,VASP},
+ file = {/Users/wasmer/Nextcloud/Zotero/Wang et al_2022_Large scale dataset of real space electronic charge density of cubic inorganic.pdf}
+}
+
@article{wangMachineLearningMaterials2020,
title = {Machine {{Learning}} for {{Materials Scientists}}: {{An Introductory Guide}} toward {{Best Practices}}},
shorttitle = {Machine {{Learning}} for {{Materials Scientists}}},
@@ -7832,6 +9045,22 @@
file = {/Users/wasmer/Nextcloud/Zotero/Wang et al_2020_Machine Learning for Materials Scientists.pdf;/Users/wasmer/Zotero/storage/PY7PFU35/acs.chemmater.html}
}
+@online{wangSymmetrybasedComputationalSearch2022,
+ title = {Symmetry-Based Computational Search for Novel Binary and Ternary {{2D}} Materials},
+ author = {Wang, Hai-Chen and Schmidt, Jonathan and Marques, Miguel A. L. and Wirtz, Ludger and Romero, Aldo H.},
+ date = {2022-12-07},
+ eprint = {2212.03975},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat},
+ doi = {10.48550/arXiv.2212.03975},
+ url = {http://arxiv.org/abs/2212.03975},
+ urldate = {2023-04-04},
+ abstract = {We present a symmetry-based exhaustive approach to explore the structural and compositional richness of two-dimensional materials. We use a ``combinatorial engine'' that constructs potential compounds by occupying all possible Wyckoff positions for a certain space group with combinations of chemical elements. These combinations are restricted by imposing charge neutrality and the Pauling test for electronegativities. The structures are then pre-optimized with a specially crafted universal neural-network force-field, before a final step of geometry optimization using density-functional theory is performed. In this way we unveil an unprecedented variety of two-dimensional materials, covering the whole periodic table in more than 30 different stoichiometries of form A\$\_n\$B\$\_m\$ or A\$\_n\$B\$\_m\$C\$\_k\$. Among the found structures we find examples that can be built by decorating nearly all Platonic and Archimedean tesselations as well as their dual Laves or Catalan tilings. We also obtain a rich, and unexpected, polymorphism for some specific compounds. We further accelerate the exploration of the chemical space of two-dimensional materials by employing machine-learning-accelerated prototype search, based on the structural types discovered in the exhaustive search. In total, we obtain around 6500 compounds, not present in previous available databases of 2D materials, with an energy of less than 250\textasciitilde meV/atom above the convex hull of thermodynamic stability.},
+ pubstate = {preprint},
+ keywords = {2D material,2DMatpedia,AML,binary systems,C2DB,CGAT,convex hull,crystal structure,crystal symmetry,M3GNet,materials discovery,materials screening,MC2D,ML,polymorphs,prediction of structure,ternary systems,thermodynamic stability,V2DB,Wyckoff positions},
+ file = {/Users/wasmer/Nextcloud/Zotero/Wang et al_2022_Symmetry-based computational search for novel binary and ternary 2D materials.pdf;/Users/wasmer/Zotero/storage/I7GDFM7H/2212.html}
+}
+
@article{wangTopologicalStatesCondensed2017,
title = {Topological States of Condensed Matter},
author = {Wang, Jing and Zhang, Shou-Cheng},
@@ -8163,6 +9392,23 @@
file = {/Users/wasmer/Nextcloud/Zotero/Winter et al_2022_Unsupervised Learning of Group Invariant and Equivariant Representations.pdf;/Users/wasmer/Zotero/storage/5PYE8XM2/2202.html}
}
+@online{woodgateInterplayMagnetismShortrange2023,
+ title = {Interplay between Magnetism and Short-Range Order in {{Ni-based}} High-Entropy Alloys: {{CrCoNi}}, {{CrFeCoNi}}, and {{CrMnFeCoNi}}},
+ shorttitle = {Interplay between Magnetism and Short-Range Order in {{Ni-based}} High-Entropy Alloys},
+ author = {Woodgate, Christopher D. and Hedlund, Daniel and Lewis, L. H. and Staunton, Julie B.},
+ date = {2023-03-01},
+ eprint = {2303.00641},
+ eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:physics},
+ doi = {10.48550/arXiv.2303.00641},
+ url = {http://arxiv.org/abs/2303.00641},
+ urldate = {2023-04-04},
+ abstract = {The impact of magnetism on predicted atomic short-range order in Ni-based high-entropy alloys is studied using a first-principles, all-electron, Landau-type linear response theory, coupled with lattice-based atomistic modelling. We perform two sets of linear-response calculations: one in which the paramagnetic state is modelled within the disordered local moment picture, and one in which systems are modelled in a magnetically ordered state. We show that the treatment of magnetism can have significant impact both on the predicted temperature of atomic ordering and also the nature of atomic order itself. In CrCoNi, we find that the nature of atomic order changes from being \$L1\_2\$-like when modelled in the paramagnetic state to MoPt\$\_2\$-like when modelled assuming the system has magnetically ordered. In CrFeCoNi, atomic correlations between Fe and the other elements present are dramatically strengthened when we switch from treating the system as magnetically disordered to magnetically ordered. Our results show it is necessary to consider the magnetic state when modelling multicomponent alloys containing mid- to late-\$3d\$ elements. Further, we suggest that there may be high-entropy alloy compositions containing \$3d\$ transition metals that will exhibit specific atomic short-range order when thermally treated in an applied magnetic field.},
+ pubstate = {preprint},
+ keywords = {/unread,CPA,DFT,high-entropy alloys,KKR,n-ary alloys,transition metals},
+ file = {/Users/wasmer/Nextcloud/Zotero/Woodgate et al_2023_Interplay between magnetism and short-range order in Ni-based high-entropy.pdf;/Users/wasmer/Zotero/storage/RAQ822ZS/2303.html}
+}
+
@online{woodQuantumComplexityTamed2022,
title = {Quantum {{Complexity Tamed}} by {{Machine Learning}}},
author = {Wood, Charlie},
@@ -8315,6 +9561,25 @@
file = {/Users/wasmer/Nextcloud/Zotero/Yamashita et al_2022_Theoretical investigation of electronic structure and orbital moment of the Sm.pdf;/Users/wasmer/Zotero/storage/BJS78D9L/authors.html}
}
+@article{yanagiGenerationModulatedMagnetic2023,
+ title = {Generation of Modulated Magnetic Structures Based on Cluster Multipole Expansion: {{Application}} to Alpha-{{Mn}} and {{CoM3Si6}}},
+ shorttitle = {Generation of Modulated Magnetic Structures Based on Cluster Multipole Expansion},
+ author = {Yanagi, Yuki and Kusunose, Hiroaki and Nomoto, Takuya and Arita, Ryotaro and Suzuki, Michi-To},
+ date = {2023-01-10},
+ journaltitle = {Physical Review B},
+ shortjournal = {Phys. Rev. B},
+ volume = {107},
+ number = {1},
+ pages = {014407},
+ publisher = {{American Physical Society}},
+ doi = {10.1103/PhysRevB.107.014407},
+ url = {https://link.aps.org/doi/10.1103/PhysRevB.107.014407},
+ urldate = {2023-03-22},
+ abstract = {We present a systematic method to automatically generate symmetry-adapted magnetic structures for a given crystal structure and general propagation vector k as an efficient approach of the analysis of complex modulated magnetic structures. The method is developed as an extension of the generation scheme based on the multipole expansion, which was demonstrated only for the propagation vector k=0 [M.-T. Suzuki et al., Phys. Rev. B 99, 174407 (2019)]. The symmetry-adapted magnetic structures characterized with an ordering vector k are obtained by mapping the multipole magnetic alignments on a virtual cluster to the periodic crystal structure with the phase factor for the wave vector k. This method provides all magnetic bases compatible with irreducible representations under a k group for a given crystal structure and wave vector k. Multiple-k magnetic structures are derived from a superposition of single-k magnetic bases related to the space group symmetry. We apply the scheme to deduce the magnetic structures of α-Mn and CoM3S6 (M=Nb, Ta), in which the large anomalous Hall effect has recently been observed in antiferromagnetic phases, and identify the magnetic structures inducing anomalous Hall effect without net magnetization. The physical phenomena originating from emergent multipoles in the ordered phases are also discussed based on the Landau theory.},
+ keywords = {/unread,AML,descriptors,feature engineering,Ferromagnetism,invariance,magnetism,ML,rec-by-kipp,spin-dependent},
+ file = {/Users/wasmer/Zotero/storage/G9EKXIZ4/Yanagi et al. - 2023 - Generation of modulated magnetic structures based .pdf;/Users/wasmer/Zotero/storage/ILBXKEJP/PhysRevB.107.html}
+}
+
@article{yangMachinelearningAcceleratedGeometry2021,
title = {Machine-Learning Accelerated Geometry Optimization in Molecular Simulation},
author = {Yang, Yilin and Jiménez-Negrón, Omar A. and Kitchin, John R.},
@@ -8398,7 +9663,6 @@
title = {Correlated Electrons: From Models to Materials},
author = {Zeller, Rudolf},
date = {2012},
- series = {Lecture {{Notes}} of the {{Autumn School}} on {{Correlated Electrons}}},
number = {PreJuSER-136393},
institution = {{Forschungszentrum Jülich GmbH Zenralbibliothek, Verlag}},
url = {https://juser.fz-juelich.de/record/136393/},
@@ -8524,9 +9788,9 @@
shorttitle = {Pushing the Limits of Atomistic Simulations towards Ultra-High Temperature},
author = {Zhang, Yanhui and Lunghi, Alessandro and Sanvito, Stefano},
date = {2019-11-08},
- number = {arXiv:1911.03307},
- eprint = {arXiv:1911.03307},
+ eprint = {1911.03307},
eprinttype = {arxiv},
+ eprintclass = {cond-mat, physics:quant-ph},
doi = {10.48550/arXiv.1911.03307},
url = {http://arxiv.org/abs/1911.03307},
urldate = {2023-02-23},
@@ -8591,6 +9855,23 @@
file = {/Users/wasmer/Nextcloud/Zotero/Zhao et al_2019_Quantum oscillations in iron-doped single crystals of the topological insulator.pdf;/Users/wasmer/Zotero/storage/GGTED6FM/Zhao et al. - 2019 - Quantum oscillations in iron-doped single crystals.pdf;/Users/wasmer/Zotero/storage/8D5JL2DQ/PhysRevB.99.html}
}
+@online{zhouComprehensiveSurveyPretrained2023,
+ title = {A {{Comprehensive Survey}} on {{Pretrained Foundation Models}}: {{A History}} from {{BERT}} to {{ChatGPT}}},
+ shorttitle = {A {{Comprehensive Survey}} on {{Pretrained Foundation Models}}},
+ author = {Zhou, Ce and Li, Qian and Li, Chen and Yu, Jun and Liu, Yixin and Wang, Guangjing and Zhang, Kai and Ji, Cheng and Yan, Qiben and He, Lifang and Peng, Hao and Li, Jianxin and Wu, Jia and Liu, Ziwei and Xie, Pengtao and Xiong, Caiming and Pei, Jian and Yu, Philip S. and Sun, Lichao},
+ date = {2023-03-30},
+ eprint = {2302.09419},
+ eprinttype = {arxiv},
+ eprintclass = {cs},
+ doi = {10.48550/arXiv.2302.09419},
+ url = {http://arxiv.org/abs/2302.09419},
+ urldate = {2023-04-14},
+ abstract = {Pretrained Foundation Models (PFMs) are regarded as the foundation for various downstream tasks with different data modalities. A PFM (e.g., BERT, ChatGPT, and GPT-4) is trained on large-scale data which provides a reasonable parameter initialization for a wide range of downstream applications. BERT learns bidirectional encoder representations from Transformers, which are trained on large datasets as contextual language models. Similarly, the generative pretrained transformer (GPT) method employs Transformers as the feature extractor and is trained using an autoregressive paradigm on large datasets. Recently, ChatGPT shows promising success on large language models, which applies an autoregressive language model with zero shot or few shot prompting. The remarkable achievements of PFM have brought significant breakthroughs to various fields of AI. Numerous studies have proposed different methods, raising the demand for an updated survey. This study provides a comprehensive review of recent research advancements, challenges, and opportunities for PFMs in text, image, graph, as well as other data modalities. The review covers the basic components and existing pretraining methods used in natural language processing, computer vision, and graph learning. Additionally, it explores advanced PFMs used for different data modalities and unified PFMs that consider data quality and quantity. The review also discusses research related to the fundamentals of PFMs, such as model efficiency and compression, security, and privacy. Finally, the study provides key implications, future research directions, challenges, and open problems in the field of PFMs. Overall, this survey aims to shed light on the research of the PFMs on scalability, security, logical reasoning ability, cross-domain learning ability, and the user-friendly interactive ability for artificial general intelligence.},
+ pubstate = {preprint},
+ keywords = {/unread,BERT,ChatGPT,few-shot learning,foundation models,GATN,GCN,General ML,GNN,GPT,graph ML,LLM,ML,transfer learning,transformer,zero-shot learning},
+ file = {/Users/wasmer/Nextcloud/Zotero/Zhou et al_2023_A Comprehensive Survey on Pretrained Foundation Models.pdf;/Users/wasmer/Zotero/storage/CWZ9H6CB/2302.html}
+}
+
@thesis{zimmermannInitioDescriptionTransverse2014,
title = {Ab Initio Description of Transverse Transport Due to Impurity Scattering in Transition-Metals},
author = {Zimmermann, Bernd},